INDEX

Explanations

complex programming constructs and syntax elements related to function definitions and calls

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

end_of_turn

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 defaultstate

-0.45

RODUCTION

-0.42

providedIn

-0.35

ạ

-0.33

 вре

-0.32

Cas

-0.32

ov

-0.30

Cas

-0.29

Caso

-0.28

нечно

-0.28

POSITIVE LOGITS

 EconPapers

0.84

 surla

0.66

出版年

0.66

StructEnd

0.63

AndEndTag

0.60

期刊论文

0.60

請繼續往下閱讀

0.59

ngdoc

0.58

Tembelea

0.58

 архивлан

0.57

Activations Density 0.017%

complex programming constructs and syntax elements related to function definitions and calls

end_of_turn

No Comments

No Known Activations