INDEX

Explanations

information related to weights of objects or animals

oai_token-act-pair · gpt-3.5-turbo

terms related to weight measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

employment

-0.73

href

-0.70

ellen

-0.68

Mub

-0.66

imposed

-0.66

ahime

-0.66

etheless

-0.65

interrupted

-0.65

internet

-0.65

esan

-0.65

POSITIVE LOGITS

 weigh

1.23

 weighing

0.95

 weights

0.92

 weighs

0.91

 scales

0.88

ighed

0.88

 weighed

0.86

 heights

0.78

 racks

0.75

 distances

0.73

Activations Density 0.013%

information related to weights of objects or animals

terms related to weight measurements

No Comments

No Known Activations