INDEX

Explanations

numerical measurements and statistical terms

oai_token-act-pair · gpt-3.5-turbo

quantitative terms and measurements related to data analysis

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ggle

-0.56

different

-0.49

otonin

-0.48

enery

-0.47

phrine

-0.46

rium

-0.46

ergy

-0.45

Chinese

-0.45

ttle

-0.45

jah

-0.45

POSITIVE LOGITS

 notwithstanding

0.76

etc

0.53

conservancy

0.52

srf

0.52

 thereof

0.51

 equivalent

0.48

 extraord

0.48

 respectively

0.48

ãĥĩãĤ£

0.47

 preferring

0.47

Activations Density 1.939%

numerical measurements and statistical terms

quantitative terms and measurements related to data analysis

No Comments

No Known Activations