INDEX

Explanations

proper nouns or people's names

oai_token-act-pair · gpt-3.5-turbo

terms associated with organizations and political groups

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

ournals

-0.68

nesday

-0.58

 camel

-0.54

idan

-0.50

 Marriott

-0.50

 showc

-0.49

 Aram

-0.49

ffect

-0.48

idious

-0.47

 cour

-0.47

POSITIVE LOGITS

ibrary

0.62

overe

0.60

abulary

0.57

otta

0.55

QL

0.55

otide

0.53

ovych

0.52

oxide

0.52

oshenko

0.51

ombat

0.50

Activations Density 1.318%

proper nouns or people's names

terms associated with organizations and political groups

No Comments

No Known Activations