EXPLANATION TYPE
oai_token-act-pair
Description
OpenAI's Automated Interpretability from paper "Language models can explain neurons in language models". Modified by Johnny Lin to add new models/context windows.
Author
OpenAI
URL
https://github.com/hijohnnylin/automated-interpretabilitySettings
Default prompts from the main branch, strategy TokenActivationPair.
Recent Explanations
numbers and numerical/quantitative information such as statistics, metrics, dates, and monetary values.
claude-4-5-haiku
334 (Thirty-Four Thousand, Three Hundred
GEMMA-3-27B
53-GEMMASCOPE-2-RES-65K
INDEX 1852
mild, hedged negative evaluations that point out minor drawbacks or limitations, often using qualifying language or “on the … side” constructions.
gpt-5
their time-management skills, as they have a tendency to
LLAMA3.1-8B-IT
15-RESID-POST-AA
INDEX 114664
statements conveying a middling, neutral appraisal in reviews—indicating something is acceptable or average rather than excellent or poor.
gpt-5
okay student in high school, and now he's struggling
LLAMA3.1-8B-IT
15-RESID-POST-AA
INDEX 6076
negative evaluative commentary in reviews, especially statements highlighting a work’s flaws, weaknesses, or lack of quality
gpt-5
The problem I had is that the most interesting parts of
LLAMA3.1-8B-IT
15-RESID-POST-AA
INDEX 58280
expressions of dissatisfaction in consumer reviews, especially complaints about poor quality, bad fit, defects, or unmet expectations.
gpt-5
because the style is great. Too bad about the execution
LLAMA3.1-8B-IT
15-RESID-POST-AA
INDEX 9301
strongly negative evaluative language indicating criticism, dissatisfaction, or derision, especially in reviews and complaints.
gpt-5
of a deceased title that should have stayed dead. Without
LLAMA3.1-8B-IT
15-RESID-POST-AA
INDEX 92200
mathematical expressions and calculations involving variables and numerical operations.
claude-4-5-haiku
13 = 3. And 11 boys would give
DEEPSEEK-R1-DISTILL-LLAMA-8B
17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
INDEX 23818
mathematical expressions and equations containing variables and numerical operations.
claude-4-5-haiku
). Again, the neighbors of 3 can be
DEEPSEEK-R1-DISTILL-LLAMA-8B
21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
INDEX 29518
domain-specific technical or formal nouns that name systems, processes, fields, measurements, or key entities in a topic (e.g., networks, data, instruments)
gpt-5
This is a type of intensity which is not the property
LLAMA3.1-8B-IT
19-RESID-POST-AA
INDEX 35399
phrases indicating someone assuming control or a role/position, especially “take over as” style leadership or responsibility transitions.
gpt-5
On:↵↵Ryan will take over full-time GM duties↵↵
LLAMA3.1-8B-IT
19-RESID-POST-AA
INDEX 9301
mentions of a specific proper-noun brand/company name (a named brand reference).
gpt-5
, so don’t let Giant’s marketing people put you
LLAMA3.1-8B-IT
19-RESID-POST-AA
INDEX 91616
mentions of entertainment awards and honors, including nominations, wins, categories, and award-show contexts.
gpt-5
including the Genie Awards, The Gemini Awards, The
LLAMA3.1-8B-IT
19-RESID-POST-AA
INDEX 54690
mentions of the legal term “certiorari” in U.S. court case citations or headings.
gpt-5
11th Cir. Certiorari denied.↵↵
LLAMA3.1-8B-IT
19-RESID-POST-AA
INDEX 118424
snippets of source code (programming tokens and identifiers).
gpt-5-mini
keep_fnames: false,↵ mangle:
LLAMA3.1-8B-IT
11-RESID-POST-AA
INDEX 6662
tokens that are parts of systematic chemical compound names (IUPAC-style fragments, numbers and hyphenated segments).
gpt-5-mini
ographic Chemicals↵3-Chloro-6-
LLAMA3.1-8B-IT
11-RESID-POST-AA
INDEX 13279
phrases where the speaker asks for help identifying something (first‑person requests/questions like "can anyone help identify this" or "what is this").
gpt-5-mini
my experience (She says it is a cactus but
LLAMA3.1-8B-IT
11-RESID-POST-AA
INDEX 109563
the neuron detects interrogative/question cues — tokens that start or appear in questions (question words and auxiliaries used to form questions).
gpt-5-mini
Which time period would you choose and why?"<|eot_id|><|start_header_id|>
LLAMA3.1-8B-IT
11-RESID-POST-AA
INDEX 8655
tokens that are part of markup/structural document tags (HTML/XML‑style tags and other structural delimiters).
gpt-5-mini
media="print" />↵ <script type="text
LLAMA3.1-8B-IT
11-RESID-POST-AA
INDEX 52056
This neuron detects first-person self-referential pronouns and tokens (e.g., "I", "me", "my", and equivalents in other languages).
gpt-5-mini
gosto de muitas coisas, desde a po
LLAMA3.1-8B-IT
11-RESID-POST-AA
INDEX 123529
questions asking about the assistant's personal attributes or identity (age, location, appearance, name).
gpt-5-mini
can you describe what you look like?<|eot_id|><|start_header_id|>assistant
LLAMA3.1-8B-IT
11-RESID-POST-AA
INDEX 77487