INDEX

Explanations

numerical and technical information within text

oai_token-act-pair · gpt-3.5-turbo

numerical data and measurements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 omission

-0.75

actionDate

-0.59

xual

-0.58

isance

-0.57

 memos

-0.55

claw

-0.53

uyomi

-0.53

ptive

-0.51

ĸļ

-0.50

 bias

-0.50

POSITIVE LOGITS

leon

0.63

luster

0.61

agall

0.60

reau

0.58

emp

0.57

istan

0.56

abet

0.54

 Ferry

0.54

atten

0.54

ppe

0.53

Activations Density 0.802%

numerical and technical information within text

numerical data and measurements

No Comments

No Known Activations