INDEX

Explanations

numbers and numerical measures

oai_token-act-pair · gpt-3.5-turbo

numerical data and statistics related to counts or endorsements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ibur

-0.75

conom

-0.68

uv

-0.66

bite

-0.63

 fumes

-0.59

 electricity

-0.57

 electrical

-0.56

 flares

-0.56

 damaged

-0.55

oward

-0.55

POSITIVE LOGITS

 numbering

1.20

 list

1.16

 Ranking

1.09

 grouping

1.07

 Lists

1.07

 alphabet

1.04

 ranking

1.03

 lists

1.01

 counting

0.98

 rankings

0.98

Activations Density 1.269%

numbers and numerical measures

numerical data and statistics related to counts or endorsements

No Comments

No Known Activations