INDEX

Explanations

symbols and formatting related to coding or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

^(@)

-0.43

 Theſe

-0.37

 >=",

-0.37

 Majefty

-0.33

 initWithFrame

-0.32

$_"

-0.31

Efq

-0.31

 Houſe

-0.30

 Chriftian

-0.30

POSITIVE LOGITS

<bos>

1.09

 udaler

0.39

нибудь

0.37

出版年

0.35

jera

0.34

 invokingState

0.34

MENAFN

0.34

例文帳に追加

0.32

multicolumn

0.30

erei

0.30

Activations Density 3.579%

symbols and formatting related to coding or markup languages

No Comments

No Known Activations