INDEX

Explanations

references to individuals involved in legal contexts, particularly focusing on patients, defendants, and inmates

oai_token-act-pair · gpt-4o-mini Triggered by @bot

references to the central participant or subject (person, animal, or designated entity) being discussed or instructed in the passage.

oai_token-act-pair · gpt-5 Triggered by @arielgoldsteinlab

people and animals

np_max-act-logits · gpt-5 Triggered by @arielgoldsteinlab

specific entity

np_max-act-logits · gemini-2.5-flash Triggered by @arielgoldsteinlab

words and pronouns referring to people, such as "child," "inmate," "she," and "they."

oai_token-act-pair · gemini-2.5-flash Triggered by @arielgoldsteinlab

Explanation could not be parsed.

eleuther_acts_top20 · gpt-5 Triggered by @arielgoldsteinlab

These are all tokens referring to a person or animal that is the subject of an action.

eleuther_acts_top20 · gemini-2.5-flash Triggered by @arielgoldsteinlab

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verläs

-0.61

shadowRadius

-0.60

ignty

-0.58

URLException

-0.57

CppCodeGen

-0.56

PickerController

-0.55

 Crimes

-0.53

landse

-0.52

sern

-0.51

positories

-0.50

POSITIVE LOGITS

évaluateur

0.63

 ujednoznacz

0.59

TestBed

0.55

who

0.53

 يتيمه

0.53

self

0.52

oids

0.50

олові