INDEX

Explanations

comparative adjectives related to improvement or deterioration

oai_token-act-pair · gpt-3.5-turbo

references to improving and declining conditions

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

 entirety

-0.68

HO

-0.65

 Bild

-0.62

chief

-0.61

 originated

-0.60

never

-0.59

former

-0.59

Area

-0.59

ieu

-0.59

 Hong

-0.57

POSITIVE LOGITS

ãĤ¼

0.90

 sidx

0.79

 traction

0.78

noticed

0.76

retty

0.75

 puberty

0.73

 acquainted

0.71

ocobo

0.71

 mileage

0.71

 destro

0.70

Activations Density 0.085%

comparative adjectives related to improvement or deterioration

references to improving and declining conditions

No Comments

No Known Activations