INDEX

Explanations

references to the news agency "The Associated Press."

oai_token-act-pair · gpt-3.5-turbo

mentions of the Associated Press in news articles

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

gone

-0.83

err

-0.78

vae

-0.76

bull

-0.75

border

-0.74

hun

-0.73

bor

-0.72

illet

-0.71

ggle

-0.71

chest

-0.70

POSITIVE LOGITS

 Associated

1.03

 Newsp

0.98

 Colleg

0.87

 Advertising

0.87

 newsp

0.84

 Press

0.83

 Association

0.82

 agre

0.81

 Encyclopedia

0.81

 conduc

0.78

Activations Density 0.005%

references to the news agency "The Associated Press."

mentions of the Associated Press in news articles

No Comments

No Known Activations