INDEX

Explanations

legal or law enforcement-related terms and actions

oai_token-act-pair · gpt-3.5-turbo

phrases related to legal or criminal charges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ortment

-0.74

eals

-0.63

itton

-0.61

ãĥ©ãĥ³

-0.59

 majesty

-0.57

emn

-0.56

_-

-0.56

igl

-0.55

nutrition

-0.55

visors

-0.54

POSITIVE LOGITS

 whatsoever

1.52

nor

1.35

 anymore

1.17

soever

0.99

 anywhere

0.97

 EVER

0.90

nor

0.83

 ever

0.78

 except

0.78

 slightest

0.75

Activations Density 0.405%

legal or law enforcement-related terms and actions

phrases related to legal or criminal charges

No Comments

No Known Activations