INDEX

Explanations

mentions of specific proper nouns, such as locations or names

oai_token-act-pair · gpt-3.5-turbo

specific identifiers and context that suggest legal or formal language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

poons

-0.62

inement

-0.58

pires

-0.56

icol

-0.54

deals

-0.52

pty

-0.51

uesday

-0.51

ById

-0.51

slaught

-0.49

essing

-0.48

POSITIVE LOGITS

hovah

0.58

nant

0.48

tera

0.46

 Birth

0.46

hearted

0.46

itol

0.44

BuyableInstoreAndOnline

0.43

ãĥĩãĤ£

0.42

ŃĶ

0.42

igenous

0.42

Activations Density 0.497%

mentions of specific proper nouns, such as locations or names

specific identifiers and context that suggest legal or formal language

No Comments

No Known Activations