INDEX

Explanations

occurrences of specific words and terms, potentially related to definitions or origins

oai_token-act-pair · gpt-3.5-turbo

terms related to definitions and explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 failures

-0.81

enaries

-0.69

iencies

-0.68

 workshops

-0.68

 resil

-0.65

 Projects

-0.65

 Improvements

-0.64

Ws

-0.64

 Integrity

-0.63

arios

-0.62

POSITIVE LOGITS

 shorthand

1.32

 slang

1.25

 coined

1.23

 acronym

1.20

 Dictionary

1.17

 dictionary

1.15

tymology

1.10

 synonymous

1.08

 abbre

1.06

 uttered

1.05

Activations Density 0.484%

occurrences of specific words and terms, potentially related to definitions or origins

terms related to definitions and explanations

No Comments

No Known Activations