INDEX

Explanations

technical or policy-related terms and concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to various societal issues and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Defin

-0.62

©¶æ

-0.55

 suffice

-0.53

é¾įå

-0.50

è¦ļéĨĴ

-0.50

Ĭ±

-0.49

ttle

-0.48

 Pixie

-0.48

£ı

-0.48

 lockout

-0.47

POSITIVE LOGITS

wise

0.57

aila

0.51

etc

0.49

tis

0.46

viol

0.44

oday

0.44

)!

0.44

 extraord

0.44

LP

0.44

ax

0.43

Activations Density 0.582%

technical or policy-related terms and concepts

terms related to various societal issues and conditions

No Comments

No Known Activations