INDEX

Explanations

proper nouns related to news articles or photo credits

oai_token-act-pair · gpt-3.5-turbo

references to photo captions and photo credits

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

iazep

-0.70

lycer

-0.70

urnal

-0.69

anmar

-0.69

gaard

-0.68

othal

-0.62

ourgeois

-0.61

oler

-0.61

ormal

-0.61

inav

-0.60

POSITIVE LOGITS

 toggle

0.67

 Mehran

0.67

Fran

0.66

 airs

0.62

 caption

0.62

 Citiz

0.61

 recess

0.61

 handles

0.61

 Shelley

0.59

 portraying

0.58

Activations Density 0.031%

proper nouns related to news articles or photo credits

references to photo captions and photo credits

No Comments

No Known Activations