INDEX

Explanations

mentions of the word "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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ktop

-0.95

arity

-0.85

İĭ

-0.76

theless

-0.76

cific

-0.71

ĸļ

-0.70

nants

-0.69

onian

-0.69

avez

-0.68

expr

-0.68

POSITIVE LOGITS

 Hills

1.00

 Reporter

0.99

 studios

0.99

 Studios

0.93

mog

0.89

 Boulevard

0.89

 Hollywood

0.86

Film

0.85

 Pictures

0.85

 blockbuster

0.82

Activations Density 0.022%

mentions of the word "Hollywood"

references to Hollywood

No Comments

No Known Activations