INDEX

Explanations

phrases related to various associations or organizations

oai_token-act-pair · gpt-3.5-turbo

references to various associations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

gone

-0.74

=-=-=-=-=-=-=-=-

-0.66

lasses

-0.65

posed

-0.63

tro

-0.62

things

-0.62

lvl

-0.62

vae

-0.61

ãĤĮ

-0.59

fm

-0.59

POSITIVE LOGITS

 Association

1.01

eers

0.95

eer

0.90

ociation

0.87

 Associ

0.85

 Confederation

0.81

uthor

0.80

 association

0.78

SPA

0.75

 Society

0.75

Activations Density 0.021%

phrases related to various associations or organizations

references to various associations and organizations

No Comments

No Known Activations