INDEX

Explanations

documents that have been posted or shared online

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "posted."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

hart

-0.69

icably

-0.68

abilia

-0.67

etus

-0.65

aldi

-0.65

 Lauder

-0.65

 Dise

-0.65

Ĭ±

-0.65

 Lanka

-0.65

idge

-0.64

POSITIVE LOGITS

 posting

0.98

posted

0.98

 postings

0.89

 posted

0.87

 posts

0.86

ulate

0.81

doctoral

0.80

 upload

0.79

uploads

0.78

gres

0.77

Activations Density 0.017%

documents that have been posted or shared online

mentions of the word "posted."

No Comments

No Known Activations