INDEX

Explanations

mentions of the word "ani" at a high activation value

oai_token-act-pair · gpt-3.5-turbo

the word "ani" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alion

-0.95

nesday

-0.94

spin

-0.84

rique

-0.80

lier

-0.79

rified

-0.78

*/(

-0.76

glers

-0.76

é¾įå¥ĳå£«

-0.75

riz

-0.75

POSITIVE LOGITS

emi

1.42

yah

1.13

Äĩ

1.01

ya

0.93

wa

0.90

yy

0.90

elson

0.87

ZI

0.86

acs

0.85

apolis

0.82

Activations Density 0.019%

mentions of the word "ani" at a high activation value

the word "ani" in various contexts

No Comments

No Known Activations