INDEX

Explanations

references 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cffff

-1.06

hare

-0.82

cream

-0.74

ymes

-0.74

hap

-0.74

sembly

-0.74

pace

-0.73

laws

-0.69

Commerce

-0.68

efficients

-0.68

POSITIVE LOGITS

 filmmaker

1.21

 documentary

1.04

 film

1.02

 filmmakers

1.02

 filmmaking

0.99

film

0.89

 documentaries

0.89

 films

0.88

 screenings

0.87

arily

0.83

Activations Density 0.034%

references to documentaries

mentions of documentaries

No Comments

No Known Activations