INDEX

Explanations

words related to various places or things, potentially proper nouns or specialized terms

oai_token-act-pair · gpt-3.5-turbo

abbreviations or acronyms related to organizations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pus

-0.59

 mars

-0.58

utical

-0.58

*/(

-0.58

 underpin

-0.57

mony

-0.57

orative

-0.57

Øª

-0.56

)=(

-0.56

 Carnival

-0.55

POSITIVE LOGITS

uthor

0.99

uay

0.79

uni

0.78

´

0.76

URI

0.74

Ã±a

0.73

CLASSIFIED

0.72

»

0.72

ugi

0.71

ailability

0.70

Activations Density 0.100%

words related to various places or things, potentially proper nouns or specialized terms

abbreviations or acronyms related to organizations or entities

No Comments

No Known Activations