INDEX

Explanations

phrases related to respect

oai_token-act-pair · gpt-3.5-turbo

references to the concept of respect

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Lans

-0.95

 concoct

-0.76

 paran

-0.70

 dreamed

-0.63

uzzle

-0.63

 enthusi

-0.63

 nerv

-0.62

 helicop

-0.61

 ferry

-0.60

NetMessage

-0.60

POSITIVE LOGITS

ability

1.43

ably

1.24

able

1.00

abilities

0.97

fully

0.96

ility

0.96

ible

0.91

ibly

0.89

FUL

0.89

ful

0.86

Activations Density 0.041%

phrases related to respect

references to the concept of respect

No Comments

No Known Activations