INDEX

Explanations

technical terms, initials, and abbreviations

oai_token-act-pair · gpt-3.5-turbo

sequences of letters that resemble names or other proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĨĴ

-0.62

ãĤ¨ãĥ«

-0.57

 Wonderland

-0.53

éĹ

-0.52

 estimated

-0.50

 Barth

-0.50

ccording

-0.49

irlf

-0.49

aughtered

-0.49

rices

-0.48

POSITIVE LOGITS

pole

0.62

Ct

0.57

 supra

0.55

cv

0.54

stown

0.54

 benches

0.53

ĸļ

0.53

pri

0.52

 edges

0.49

lev

0.49

Activations Density 1.566%

technical terms, initials, and abbreviations

sequences of letters that resemble names or other proper nouns

No Comments

No Known Activations