INDEX

Explanations

the word "cover" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to magazine covers

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sabha

-0.83

OTAL

-0.78

uct

-0.71

phas

-0.71

onge

-0.70

rian

-0.70

rous

-0.69

rians

-0.68

ntil

-0.63

utton

-0.62

POSITIVE LOGITS

ages

1.03

 cover

0.94

 covers

0.88

Cover

0.86

alls

0.84

 illustration

0.82

="#

0.77

AGE

0.76

 Cover

0.76

cover

0.75

Activations Density 0.029%

the word "cover" in various contexts

references to magazine covers

No Comments

No Known Activations