INDEX

Explanations

mentions of the word "Wonder"

oai_token-act-pair · gpt-3.5-turbo

references to the character "Wonder Woman."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

aution

-0.78

 destro

-0.77

 manslaughter

-0.72

escription

-0.70

EStream

-0.70

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.65

 seiz

-0.64

 separat

-0.63

 occas

-0.63

 disg

-0.62

POSITIVE LOGITS

bolt

0.99

fully

0.98

stru

0.93

 Woman

0.91

efully

0.90

FUL

0.90

storms

0.89

kids

0.88

bol

0.86

power

0.86

Activations Density 0.036%

mentions of the word "Wonder"

references to the character "Wonder Woman."

No Comments

No Known Activations