INDEX

Explanations

phrases related to documentaries

oai_token-act-pair · gpt-3.5-turbo

mentions of documentaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

cffff

-0.84

arching

-0.84

adding

-0.82

hr

-0.75

Commerce

-0.73

olen

-0.72

adies

-0.72

ulz

-0.72

sembly

-0.71

illes

-0.71

POSITIVE LOGITS

 documentary

1.30

 documentaries

1.05

 filmmaker

1.03

 filmmaking

0.98

 film

0.92

 filmmakers

0.87

Film

0.82

document

0.81

thouse

0.79

 films

0.78

Activations Density 0.012%

phrases related to documentaries

mentions of documentaries

No Comments

No Known Activations