INDEX

Explanations

phrases expressing uncertainty or doubt

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Bloomberg

-0.62

odder

-0.59

soever

-0.58

onde

-0.57

flower

-0.56

 frequ

-0.56

HAEL

-0.53

ario

-0.53

ials

-0.51

Land

-0.51

POSITIVE LOGITS

 sure

1.38

 yourselves

1.06

 certain

1.04

 yourself

0.99

 ourselves

0.97

 instance

0.95

 oneself

0.94

geries

0.92

 starters

0.92

 example

0.90

Activations Density 0.080%

phrases expressing uncertainty or doubt

phrases indicating uncertainty or conditions

No Comments

No Known Activations