INDEX

Explanations

phrases indicating surprise or disbelief

oai_token-act-pair · gpt-3.5-turbo

phrases that express similarity or comparisons

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

•layer 6 - surprise

No Comments

Negative Logits

Published

-0.81

Ô

-0.75

acia

-0.72

arta

-0.68

oca

-0.68

OE

-0.65

obook

-0.65

essing

-0.65

Added

-0.64

MG

-0.63

POSITIVE LOGITS

lihood

1.08

lier

0.69

 lettuce

0.66

 yours

0.65

 hers

0.62

 pneumonia

0.61

 ours

0.59

sembly

0.58

 homework

0.57

 Sark

0.56

Activations Density 0.055%

phrases indicating surprise or disbelief

phrases that express similarity or comparisons

No Comments

No Known Activations