INDEX

Explanations

information or phrases related to legal or formal documents

oai_token-act-pair · gpt-3.5-turbo

the word "from" indicating sources of information or citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

pled

-0.74

psey

-0.71

ample

-0.67

 consecut

-0.67

inse

-0.66

 guarantee

-0.65

atern

-0.64

abeth

-0.64

 cohesion

-0.63

 sucker

-0.62

POSITIVE LOGITS

 Flavoring

0.91

 Pastebin

0.88

 Encyclopedia

0.75

Wow

0.73

io

0.72

 Sina

0.72

 Subtle

0.72

 Wikimedia

0.72

 Manga

0.72

 TheNitromeFan

0.71

Activations Density 0.029%

information or phrases related to legal or formal documents

the word "from" indicating sources of information or citations

No Comments

No Known Activations