INDEX

Explanations

words related to political figures or entities

oai_token-act-pair · gpt-3.5-turbo

specific names or acronyms, particularly related to individuals or organizations

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

advertising

-0.78

Chel

-0.64

 fulfillment

-0.61

Environment

-0.59

 Rohing

-0.59

ability

-0.59

\<

-0.58

fts

-0.58

uations

-0.58

verse

-0.58

POSITIVE LOGITS

EStream

0.84

illion

0.79

xual

0.71

)]

0.66

auri

0.66

arat

0.63

apo

0.63

uliffe

0.61

reau

0.61

xon

0.60

Activations Density 0.184%

words related to political figures or entities

specific names or acronyms, particularly related to individuals or organizations

No Comments

No Known Activations