INDEX

Explanations

phrases indicating the removal or elimination of something

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of eliminating or getting rid of something

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

foreseen

-0.65

anwhile

-0.60

 Luxembourg

-0.54

 concess

-0.54

 Amos

-0.53

 corrective

-0.53

 McDonnell

-0.53

 Berm

-0.53

enegger

-0.53

 appre

-0.52

POSITIVE LOGITS

of

0.97

icide

0.83

icides

0.81

igators

0.77

Of

0.76

ges

0.76

ged

0.74

itive

0.73

ta

0.72

escent

0.71

Activations Density 0.023%

phrases indicating the removal or elimination of something

phrases related to the concept of eliminating or getting rid of something

No Comments

No Known Activations