INDEX

Explanations

references to contributors or entities contributing to various projects or publications

oai_token-act-pair · gpt-3.5-turbo

mentions of contributors and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Lumpur

-0.83

Lob

-0.77

isen

-0.74

dar

-0.70

plane

-0.66

ecause

-0.65

creen

-0.65

 Rite

-0.65

scape

-0.62

ZI

-0.62

POSITIVE LOGITS

 contributor

0.91

 contributors

0.90

 Contribut

0.89

 laureate

0.88

hip

0.80

 contributing

0.80

iosyncr

0.75

 contributions

0.74

iaries

0.73

idency

0.70

Activations Density 0.016%

references to contributors or entities contributing to various projects or publications

mentions of contributors and their roles

No Comments

No Known Activations