INDEX

Explanations

years

oai_token-act-pair · gpt-3.5-turbo

references to specific years and their significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ULE

-0.74

raised

-0.72

HC

-0.69

apple

-0.68

Offline

-0.66

GA

-0.63

illary

-0.63

displayText

-0.62

raise

-0.62

ALE

-0.61

POSITIVE LOGITS

eteen

1.34

teen

1.17

Eight

1.03

irteen

1.02

ety

0.99

Twenty

0.96

ishers

0.96

 Twenty

0.94

 Thousand

0.93

ixty

0.90

Activations Density 0.012%

years

references to specific years and their significance

No Comments

No Known Activations