INDEX

Explanations

mentions of the word "president."

oai_token-act-pair · gpt-3.5-turbo

mentions of the president

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

sbm

-0.76

 exting

-0.72

PsyNetMessage

-0.70

acements

-0.68

srf

-0.67

 Casting

-0.67

 Flavoring

-0.66

Î³

-0.66

 Mortal

-0.64

ENE

-0.64

POSITIVE LOGITS

ially

0.89

's

0.80

clinton

0.74

 nominated

0.73

 vetoed

0.72

manship

0.72

 presidency

0.72

 Lyndon

0.71

 emer

0.71

 administration

0.70

Activations Density 0.056%

mentions of the word "president."

mentions of the president

No Comments

No Known Activations