INDEX

Explanations

movie related terms like "remake" and "adaptation"

oai_token-act-pair · gpt-3.5-turbo

terms related to adaptations and remakes of movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

maxwell

-0.78

lear

-0.76

itud

-0.76

negie

-0.72

fw

-0.64

nutrition

-0.64

itness

-0.64

ideon

-0.63

kefeller

-0.63

hair

-0.63

POSITIVE LOGITS

 thereof

1.27

 version

0.90

of

0.77

 versions

0.77

 remake

0.74

 adaptation

0.71

 copy

0.69

 embod

0.68

 reprint

0.67

 edition

0.67

Activations Density 0.146%

movie related terms like "remake" and "adaptation"

terms related to adaptations and remakes of movies

No Comments

No Known Activations