INDEX

Explanations

the word "repository" and potentially other related words such as "github" and "model".

oai_token-act-pair · gemini-2.0-flash

repository

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Repository

-1.73

 Repository

-1.62

repository

-1.56

 repository

-1.49

Repo

-1.30

 Repo

-1.20

repo

-1.20

 repositories

-1.18

 repo

-1.14

getRepository

-1.11

POSITIVE LOGITS

 barefoot

0.45

劈

0.43

ึกษา

0.43

geon

0.43

 comfort

0.43

干

0.43

Bew

0.42

circledR

0.41

mery

0.40

Tra

0.40

Activations Density 2.983%

the word "repository" and potentially other related words such as "github" and "model".

repository

No Comments

No Known Activations