INDEX

Explanations

references to the reader or "reader" language throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HideFlags

-0.69

matchCondition

-0.63

帖最后由

-0.61

MultipartFile

-0.56

DMETHOD

-0.53

reonine

-0.53

mybatisplus

-0.52

cataly

-0.52

 disponibilités

-0.52

ArgsConstructor

-0.51

POSITIVE LOGITS

 reader

4.40

 Reader

4.01

reader

3.89

Reader

3.74

 READER

3.33

 Readers

3.23

 readers

3.19

readers

3.03

Readers

2.88

 leitor

2.27

Activations Density 0.094%

references to the reader or "reader" language throughout the text

No Comments

No Known Activations