INDEX

Explanations

mentions of the word 'gram'

oai_token-act-pair · gpt-3.5-turbo

references to measurements of weight, specifically in grams

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

Downloadha

-0.72

Never

-0.71

 Occupations

-0.69

 Retirement

-0.68

 Rapp

-0.68

 Citizens

-0.66

ESCO

-0.64

 Palmer

-0.64

quished

-0.63

Madison

-0.62

POSITIVE LOGITS

matical

1.57

matically

1.36

ophone

1.14

 gram

1.06

gram

1.01

matic

0.95

ophon

0.91

 Gram

0.89

ming

0.89

mers

0.88

Activations Density 0.011%

mentions of the word 'gram'

references to measurements of weight, specifically in grams

No Comments

No Known Activations