INDEX

Explanations

mentions of specific document parts or sections labeled as "Part X."

oai_token-act-pair · gpt-3.5-turbo

references to parts or sections of a document or report

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

IFrame

Link

Negative Logits

 arms

-0.71

 gifted

-0.68

 mentally

-0.64

berman

-0.61

 throats

-0.60

urses

-0.59

llular

-0.59

kn

-0.59

incinn

-0.59

 crawl

-0.59

POSITIVE LOGITS

icularly

1.06

ners

0.99

Part

0.98

 Part

0.97

ially

0.96

ITION

0.93

ition

0.87

icipated

0.84

nered

0.84

ICLE

0.84

Activations Density 0.008%

mentions of specific document parts or sections labeled as "Part X."

references to parts or sections of a document or report

No Known Activations