INDEX

Explanations

words related to the entertainment industry, specifically Hollywood

oai_token-act-pair · gpt-3.5-turbo

references to Hollywood

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

ktop

-0.95

İĭ

-0.86

arity

-0.83

avez

-0.81

theless

-0.79

cific

-0.79

etheless

-0.78

nants

-0.73

unin

-0.72

ombo

-0.72

POSITIVE LOGITS

 Reporter

1.05

 studios

1.00

 Studios

1.00

 Hills

1.00

 Hollywood

0.93

 Boulevard

0.89

 Pictures

0.89

 movies

0.86

mog

0.85

 blockbuster

0.84

Activations Density 0.029%

words related to the entertainment industry, specifically Hollywood

references to Hollywood

No Comments

No Known Activations