INDEX

Explanations

politicians' names and geographical locations

oai_token-act-pair · gpt-3.5-turbo

references to political figures and their affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

heid

-0.84

xon

-0.80

estern

-0.79

abwe

-0.75

yout

-0.72

agate

-0.70

tty

-0.69

ascript

-0.69

allo

-0.69

Zot

-0.64

POSITIVE LOGITS

ULAR

0.73

 remission

0.61

 metic

0.60

aez

0.58

utive

0.58

Marie

0.57

 isolation

0.57

 faint

0.56

 Saiyan

0.56

 Lauder

0.56

Activations Density 0.315%

politicians' names and geographical locations

references to political figures and their affiliations

No Comments

No Known Activations