INDEX

Explanations

words related to voting and voter-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to voter registration and electoral issues

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

Ļ½

-0.77

ensed

-0.77

Else

-0.76

ahime

-0.73

estial

-0.73

 Flavoring

-0.73

eton

-0.70

 Palestin

-0.69

SourceFile

-0.68

alin

-0.67

POSITIVE LOGITS

 turnout

1.11

 disenfranch

0.90

 registration

0.87

 voter

0.85

 fraud

0.79

 voting

0.79

ndum

0.78

 suppression

0.77

 booth

0.76

 canv

0.73

Activations Density 0.015%

words related to voting and voter-related terms

terms related to voter registration and electoral issues

No Comments

No Known Activations