INDEX

Explanations

references to the New York Times

oai_token-act-pair · gpt-3.5-turbo

mentions of "The New York Times."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

reating

-0.80

ded

-0.74

rals

-0.74

resent

-0.73

utch

-0.73

icides

-0.72

iov

-0.72

ressive

-0.71

rown

-0.70

leased

-0.70

POSITIVE LOGITS

 Square

0.85

 bestselling

0.85

 Magazine

0.84

 Dispatch

0.75

 Literary

0.75

 Reader

0.74

 Publishing

0.73

 Observer

0.72

 Mail

0.71

 conclud

0.71

Activations Density 0.024%

references to the New York Times

mentions of "The New York Times."

No Comments

No Known Activations