INDEX

Explanations

references to sports stadiums and related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of stadiums

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

dit

-0.69

 Grimm

-0.66

later

-0.65

yan

-0.64

Balt

-0.64

bery

-0.64

laughter

-0.64

zie

-0.63

bart

-0.63

yon

-0.62

POSITIVE LOGITS

 stadiums

1.21

 stadium

1.15

 Stadium

0.96

adium

0.92

 seating

0.90

 scoreboard

0.90

 renovation

0.87

 renovations

0.85

 dome

0.81

 announcer

0.78

Activations Density 0.048%

references to sports stadiums and related terms

mentions of stadiums

No Comments

No Known Activations