INDEX

Explanations

words related to events or occasions, specifically focusing on film premieres

oai_token-act-pair · gpt-3.5-turbo

references to film premieres

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gm

-0.74

azel

-0.74

psy

-0.74

bath

-0.72

loss

-0.70

sol

-0.70

tem

-0.69

mil

-0.68

elong

-0.67

sie

-0.66

POSITIVE LOGITS

 premiere

1.34

 Premiere

1.15

 premie

1.13

 premier

0.96

 screening

0.89

 screenings

0.88

 airing

0.81

 premiered

0.79

 starring

0.78

APR

0.76

Activations Density 0.006%

words related to events or occasions, specifically focusing on film premieres

references to film premieres

No Comments

No Known Activations