INDEX

Explanations

numerical measurements and lengths

oai_token-act-pair · gpt-3.5-turbo

references to measurements of length

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

eers

-0.95

eer

-0.85

eering

-0.76

dinand

-0.73

unin

-0.70

oras

-0.65

 Jarrett

-0.64

ILLE

-0.63

lar

-0.63

leck

-0.62

POSITIVE LOGITS

shed

1.03

 length

0.96

 lengths

0.96

iest

0.85

length

0.81

running

0.78

cut

0.78

Length

0.78

entimes

0.76

ftime

0.76

Activations Density 0.022%

numerical measurements and lengths

references to measurements of length

No Comments

No Known Activations