INDEX

Explanations

occurrences of coding-related functions and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 surla

-0.48

 "..\..\

-0.44

enderal

-0.44

+"'

-0.43

valg

-0.41

toMatchSnapshot

-0.41

 moot

-0.41

sleeve

-0.41

ղ

-0.40

Cara

-0.40

POSITIVE LOGITS

 split

1.38

 Split

1.33

split

1.30

Split

1.27

StringTokenizer

1.26

 StringTokenizer

1.22

 splits

1.17

 splitting

1.16

SPLIT

1.14

sscanf

1.09

Activations Density 0.124%

occurrences of coding-related functions and parameters

No Comments

No Known Activations