INDEX

Explanations

words related to bears

oai_token-act-pair · gpt-3.5-turbo

references to "Bear" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

istry

-0.81

selves

-0.74

lectic

-0.70

opus

-0.70

imates

-0.68

inel

-0.66

ubuntu

-0.66

ADRA

-0.66

ablishment

-0.66

isters

-0.66

POSITIVE LOGITS

bear

0.98

Gry

0.89

cub

0.89

beit

0.88

 Bears

0.88

hug

0.87

 Grizz

0.84

xual

0.84

cats

0.82

 hugs

0.80

Activations Density 0.036%

words related to bears

references to "Bear" and related terms

No Comments

No Known Activations