INDEX

Explanations

numbers or statistics mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

references to quantitative data or statistics

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

ModLoader

-0.78

INTON

-0.74

nee

-0.70

rib

-0.65

atever

-0.65

Â¯Â¯

-0.64

missible

-0.64

ichen

-0.64

sole

-0.64

anism

-0.63

POSITIVE LOGITS

 numbers

0.99

 Numbers

0.98

metry

0.81

 percentages

0.79

paces

0.76

 figures

0.76

omial

0.75

 averages

0.75

ynthesis

0.73

 digits

0.72

Activations Density 0.022%

numbers or statistics mentioned in the text

references to quantitative data or statistics

No Comments

No Known Activations