INDEX

Explanations

phrases related to comparing or contrasting different entities

oai_token-act-pair · gpt-3.5-turbo

references to notable individuals or entities

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

 teasp

-0.75

oided

-0.68

rang

-0.68

quartered

-0.68

 mastery

-0.66

ially

-0.64

 somew

-0.63

Ô

-0.63

ione

-0.63

rote

-0.62

POSITIVE LOGITS

 Philippe

0.80

 Crist

0.79

 ours

0.74

 Pedro

0.74

 Terry

0.73

yip

0.72

 Julius

0.72

 Burk

0.72

 Jeremiah

0.71

 Neil

0.70

Activations Density 0.051%

phrases related to comparing or contrasting different entities

references to notable individuals or entities

No Comments

No Known Activations