INDEX

Explanations

references to sports officials, specifically referees

oai_token-act-pair · gpt-3.5-turbo

references to referees in sports contexts

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

Sea

-0.72

izoph

-0.71

ocobo

-0.70

stem

-0.67

yles

-0.66

VILLE

-0.65

 VIDEOS

-0.65

 Horses

-0.65

ESE

-0.64

tom

-0.63

POSITIVE LOGITS

eree

1.05

 referees

0.94

 referee

0.94

esses

0.82

 stopp

0.78

 rigged

0.76

 examiner

0.75

ÃŃa

0.73

bage

0.70

iquette

0.70

Activations Density 0.034%

references to sports officials, specifically referees

references to referees in sports contexts

No Comments

No Known Activations