INDEX

Explanations

words related to titles of media works, such as movies, TV shows, and books

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically closing parentheses

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

 artif

-0.78

onite

-0.75

 answ

-0.73

omorphic

-0.73

omore

-0.72

tering

-0.71

bably

-0.71

bage

-0.71

bing

-0.70

 footing

-0.70

POSITIVE LOGITS

 âĵĺ

0.77

 Committees

0.76

=>

0.76

 Races

0.75

 Frames

0.73

ATURE

0.73

 Modes

0.71

Ltd

0.70

 Shows

0.70

Activations Density 0.122%

words related to titles of media works, such as movies, TV shows, and books

punctuation marks, specifically closing parentheses

No Comments

No Known Activations