INDEX

Explanations

phrases related to acting roles and film productions

oai_token-act-pair · gpt-3.5-turbo

elements related to film and performance 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 learners

-0.73

 limitation

-0.72

 weeds

-0.71

anders

-0.71

 certific

-0.70

regulated

-0.69

usted

-0.68

 limb

-0.68

chwitz

-0.68

learn

-0.66

POSITIVE LOGITS

 Ghostbusters

0.98

 Episode

0.92

 commercials

0.87

 Cartoon

0.81

 Playboy

0.80

ITV

0.80

TV

0.79

 sitcom

0.76

 movie

0.75

MTV

0.75

Activations Density 0.289%

phrases related to acting roles and film productions

elements related to film and performance credits

No Comments

No Known Activations