INDEX

Explanations

offensive and derogatory language, including profanity and insults

oai_token-act-pair · gpt-3.5-turbo

derogatory terms and insults

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

apers

-0.82

mental

-0.79

enza

-0.76

ctica

-0.74

ainted

-0.73

ENC

-0.73

âĹ¼

-0.72

undai

-0.72

ORN

-0.71

inguished

-0.71

POSITIVE LOGITS

 bitch

1.33

buster

1.01

fuck

0.96

 asses

0.96

hole

0.95

holes

0.91

 cunt

0.88

 bastard

0.86

 whore

0.84

 bast

0.81

Activations Density 0.008%

offensive and derogatory language, including profanity and insults

derogatory terms and insults

No Comments

No Known Activations