INDEX

Explanations

phrases related to intense emotional states or actions

oai_token-act-pair · gpt-3.5-turbo

references to reading and related concepts

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

 Awards

-0.72

 Briggs

-0.72

 Extras

-0.66

 Extensions

-0.66

AU

-0.64

 Noir

-0.63

Fram

-0.62

Rai

-0.62

çīĪ

-0.61

BOOK

-0.61

POSITIVE LOGITS

iencies

0.94

itably

0.92

uous

0.91

nesses

0.86

ingly

0.86

ened

0.83

assing

0.83

cest

0.81

uously

0.80

itary

0.80

Activations Density 0.137%

phrases related to intense emotional states or actions

references to reading and related concepts

No Comments

No Known Activations