INDEX

Explanations

numbers and scientific or technical terms

oai_token-act-pair · gpt-3.5-turbo

terms related to statistical data and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ividual

-0.77

ecause

-0.65

 ItemLevel

-0.64

onga

-0.60

ogun

-0.60

him

-0.59

wark

-0.59

olean

-0.59

iard

-0.53

ruary

-0.53

POSITIVE LOGITS

 antioxid

0.89

natureconservancy

0.79

 tradem

0.79

 millenn

0.79

 Seym

0.78

Balt

0.77

ß

0.75

kefeller

0.73

PDATE

0.72

GoldMagikarp

0.72

Activations Density 7.788%

numbers and scientific or technical terms

terms related to statistical data and measurements

No Comments

No Known Activations