INDEX

Explanations

references to different sports

oai_token-act-pair · gpt-3.5-turbo

mentions of various sports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ignt

-0.74

idges

-0.69

 sidx

-0.64

andering

-0.63

ppelin

-0.62

 defective

-0.62

 sunshine

-0.62

inki

-0.62

ading

-0.60

inois

-0.60

POSITIVE LOGITS

sw

1.25

scar

1.08

nell

0.98

sc

0.85

spe

0.83

manship

0.81

club

0.81

Sport

0.80

enegger

0.78

nel

0.78

Activations Density 0.010%

references to different sports

mentions of various sports

No Comments

No Known Activations