INDEX

Explanations

titles or headings annotated with special symbols

oai_token-act-pair · gpt-3.5-turbo

titles of articles or reports

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

 shroud

-0.81

 destro

-0.74

 range

-0.73

 sear

-0.72

 fragmentation

-0.71

 sofa

-0.70

 hemor

-0.69

Roc

-0.66

 leap

-0.66

 neighb

-0.65

POSITIVE LOGITS

ª

1.27

¹

1.20

ł

1.17

ı

1.12

Ĵ

1.03

³

0.99

¡

0.99

ĳ

0.98

«

0.94

»

0.93

Activations Density 0.151%

titles or headings annotated with special symbols

titles of articles or reports

No Comments

No Known Activations