INDEX

Explanations

institutions and organizations

oai_token-act-pair · gpt-3.5-turbo

references to research institutions and organizations

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

 misdem

-0.79

 pageant

-0.75

 mascara

-0.73

 shine

-0.71

 kittens

-0.69

udeau

-0.68

 retribution

-0.66

 ancest

-0.66

 glory

-0.65

 derby

-0.64

POSITIVE LOGITS

 Against

0.80

ronic

0.78

rence

0.72

eworks

0.71

intern

0.70

 Room

0.70

 Scientific

0.69

lon

0.69

Office

0.69

onia

0.69

Activations Density 0.153%

institutions and organizations

references to research institutions and organizations

No Comments

No Known Activations