INDEX

Explanations

phrases related to political figures named "Muammar Gaddafi."

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals named "Mu" or related characters

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

 Eleven

-0.72

wip

-0.71

å§«

-0.71

 BART

-0.69

*/(

-0.69

 Dispatch

-0.66

 Ajax

-0.64

UID

-0.63

 Otto

-0.63

 Carney

-0.62

POSITIVE LOGITS

lder

1.19

zik

1.03

ahah

1.03

hammad

1.00

selage

0.96

udge

0.96

 Klux

0.95

jah

0.95

osh

0.93

gha

0.93

Activations Density 0.008%

phrases related to political figures named "Muammar Gaddafi."

references to specific individuals named "Mu" or related characters

No Comments

No Known Activations