INDEX

Explanations

names of individuals and their associated information

oai_token-act-pair · gpt-3.5-turbo

phrases related to legal or criminal matters

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

 overhead

-0.62

},

-0.60

>[

-0.59

Hello

-0.59

Frag

-0.59

Scar

-0.57

................

-0.57

âĶĢâĶĢ

-0.57

Give

-0.56

Nature

-0.56

POSITIVE LOGITS

enegger

0.84

ften

0.71

 photographed

0.71

©¶æ

0.70

 additionally

0.70

 vividly

0.69

 furthermore

0.68

 also

0.67

icer

0.66

ersen

0.66

Activations Density 0.533%

names of individuals and their associated information

phrases related to legal or criminal matters

No Comments

No Known Activations