INDEX

Explanations

references to the character "Wonder Woman"

oai_token-act-pair · gpt-3.5-turbo

mentions and contexts related to "Wonder Woman."

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

aution

-0.88

 destro

-0.85

escription

-0.80

EStream

-0.80

oaded

-0.77

ornia

-0.76

interstitial

-0.76

ournal

-0.76

ccording

-0.75

 manslaughter

-0.73

POSITIVE LOGITS

 Woman

0.99

bolt

0.92

storms

0.90

frey

0.87

wall

0.85

Woman

0.83

 Wonder

0.82

 Meter

0.81

stru

0.81

 Bread

0.81

Activations Density 0.023%

references to the character "Wonder Woman"

mentions and contexts related to "Wonder Woman."

No Comments

No Known Activations