INDEX

Explanations

references to the news network Fox

oai_token-act-pair · gpt-3.5-turbo

references to the Fox News network

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

assy

-0.64

orically

-0.62

estones

-0.62

 captcha

-0.61

rians

-0.59

quo

-0.59

apter

-0.58

iments

-0.57

 Edison

-0.57

 rusty

-0.57

POSITIVE LOGITS

conn

1.59

 News

1.11

News

1.06

woods

1.00

croft

1.00

borough

0.98

 Broadcasting

0.92

Sports

0.92

cat

0.89

 Sports

0.88

Activations Density 0.035%

references to the news network Fox

references to the Fox News network

No Comments

No Known Activations