INDEX

Explanations

mentions of the word "Congress"

oai_token-act-pair · gpt-3.5-turbo

mentions of Congress

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

MM

-0.72

srf

-0.65

 Sussex

-0.63

âķĲâķĲ

-0.63

imilar

-0.62

 Britann

-0.62

-0.61

Var

-0.61

jiang

-0.60

 Vertical

-0.60

POSITIVE LOGITS

woman

1.27

ional

1.14

men

0.93

crit

0.87

ername

0.82

arians

0.81

member

0.81

 appropriated

0.80

women

0.75

inition

0.74

Activations Density 0.022%

mentions of the word "Congress"

mentions of Congress

No Comments

No Known Activations