INDEX

Explanations

specific mentions of events being signed into law

oai_token-act-pair · gpt-3.5-turbo

instances of the word "signed" in relation to legislative or formal actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Islands

-0.71

 Surviv

-0.69

asma

-0.68

 Adventures

-0.66

gypt

-0.63

rough

-0.63

 nerv

-0.61

adish

-0.60

ooked

-0.60

 complexion

-0.58

POSITIVE LOGITS

atories

1.13

atory

0.89

*/(

0.89

ificant

0.87

ificantly

0.84

interstitial

0.82

sign

0.82

chant

0.82

gement

0.80

gements

0.78

Activations Density 0.029%

specific mentions of events being signed into law

instances of the word "signed" in relation to legislative or formal actions

No Comments

No Known Activations