INDEX

Explanations

company names

oai_token-act-pair · gpt-3.5-turbo

references to web URLs and associated content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ĸļ

-0.80

xual

-0.54

 Lauder

-0.54

antage

-0.53

Mub

-0.52

 Vaugh

-0.52

 citiz

-0.50

 Ambro

-0.49

dden

-0.49

Rae

-0.48

POSITIVE LOGITS

Ĥİ

0.58

iasco

0.58

hemy

0.54

tes

0.50

USD

0.49

thur

0.49

tein

0.48

Äį

0.47

Å¡

0.47

INC

0.47

Activations Density 1.391%

company names

references to web URLs and associated content

No Comments

No Known Activations