INDEX

Explanations

code syntax elements, particularly related to definitions and declarations in programming

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

repeated string or number fields

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

Nationalité

-0.38

reportWebVitals

-0.36

 στα

-0.31

AppCompatTheme

-0.30

usammen

-0.28

sm

-0.27

意

-0.27

 Ensino

-0.27

מצ

-0.27

 PRIOR

-0.27

POSITIVE LOGITS

 >=",

0.63

addCriterion

0.63

دانشنامهٔ

0.60

writeFieldEnd

0.60

 Biôgrafia

0.59

Microkernel

0.58

transQ

0.57

Ӕ

0.57

ControllerAdvice

0.57

Cyfarwyddwr

0.57

Activations Density 0.152%

code syntax elements, particularly related to definitions and declarations in programming

repeated string or number fields

No Comments

No Known Activations