INDEX

Explanations

references to numerical figures and counts

oai_token-act-pair · gpt-3.5-turbo

references to groups and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

entimes

-0.81

vik

-0.78

DERR

-0.62

ople

-0.62

rifice

-0.61

abre

-0.61

rison

-0.60

rag

-0.60

erb

-0.59

assetsadobe

-0.59

POSITIVE LOGITS

 respectively

0.92

 composing

0.89

 listed

0.81

 vying

0.81

 consecut

0.80

 finalists

0.79

 surveyed

0.76

 mentioned

0.75

viz

0.73

 simultaneously

0.70

Activations Density 0.327%

references to numerical figures and counts

references to groups and institutions

No Comments

No Known Activations