INDEX

Explanations

mentions of law enforcement professionals

oai_token-act-pair · gpt-3.5-turbo

references to police officers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

FORE

-0.89

sbm

-0.83

committee

-0.72

Downloadha

-0.70

xual

-0.68

*/(

-0.65

veyard

-0.65

WAYS

-0.64

schild

-0.64

GGGGGGGG

-0.64

POSITIVE LOGITS

yrights

1.19

rodu

1.02

ious

0.94

cop

0.93

yright

0.92

enhagen

0.88

icker

0.87

yp

0.79

ortion

0.78

eland

0.72

Activations Density 0.004%

mentions of law enforcement professionals

references to police officers

No Comments

No Known Activations