INDEX

Explanations

references to voter-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to voter registration and participation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ensed

-0.79

ahime

-0.74

Else

-0.73

Ļ½

-0.73

estial

-0.71

ensor

-0.70

é¾

-0.69

 Palestin

-0.67

tions

-0.67

ologies

-0.66

POSITIVE LOGITS

 turnout

1.05

 disenfranch

0.85

 registration

0.84

 fraud

0.81

 imperson

0.79

 voter

0.78

 suppression

0.75

igators

0.73

 voting

0.71

ndum

0.69

Activations Density 0.018%

references to voter-related terms

terms related to voter registration and participation

No Comments

No Known Activations