INDEX

Explanations

derogatory terms or insults directed at individuals

oai_token-act-pair · gpt-3.5-turbo

derogatory labels or insults used in social or political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

foreseen

-0.73

 adjoining

-0.73

 conclud

-0.70

 inclined

-0.68

 effected

-0.64

 governed

-0.63

 amplified

-0.63

 contexts

-0.62

 resided

-0.62

 adjacent

-0.60

POSITIVE LOGITS

 liar

0.85

0.79

0.76

 traitor

0.76

fascist

0.75

 junk

0.75

Tes

0.74

 nuisance

0.74

 coward

0.72

ãĢİ

0.72

Activations Density 0.123%

derogatory terms or insults directed at individuals

derogatory labels or insults used in social or political contexts

No Comments

No Known Activations