INDEX

Explanations

occurrences of the word "in"

oai_token-act-pair · gpt-3.5-turbo

phrases indicating location or presence in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

iction

-0.79

ieties

-0.66

 depended

-0.65

 maintains

-0.65

 taught

-0.64

ulates

-0.63

 abstinence

-0.62

manship

-0.62

 thanked

-0.61

urance

-0.61

POSITIVE LOGITS

 silhouette

0.84

 afar

0.83

Picture

0.80

 theaters

0.79

 trailers

0.78

 pictures

0.77

 screenshots

0.76

photos

0.75

 CCTV

0.75

 Trailer

0.74

Activations Density 0.292%

occurrences of the word "in"

phrases indicating location or presence in various contexts

No Comments

No Known Activations