INDEX

Explanations

locations or names of places

oai_token-act-pair · gpt-3.5-turbo

geographical names and locations

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

Reviewed

-0.81

 commissions

-0.69

kefeller

-0.66

ruary

-0.65

CTR

-0.63

 cigars

-0.62

udeau

-0.61

interstitial

-0.61

achine

-0.60

 squares

-0.59

POSITIVE LOGITS

querque

0.85

 Wonderland

0.82

ãĥīãĥ©ãĤ´ãĥ³

0.78

ĪĴ

0.75

¥µ

0.73

iannopoulos

0.72

umeric

0.71

zona

0.71

ģĸ

0.70

«ĺ

0.68

Activations Density 0.435%

locations or names of places

geographical names and locations

No Comments

No Known Activations