INDEX

Explanations

occurrences of programming-related terms and queries

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

filter expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 المعيارى

-0.57

 كومونز

-0.55

rungsseite

-0.55

IsContent

-0.52

principalColumn

-0.51

出版年

-0.50

Архівовано

-0.50

 ***!

-0.48

SourceChecksum

-0.46

UserScript

-0.46

POSITIVE LOGITS

URLException

0.47

 charité

0.40

őle

0.40

Bauer

0.40

Java

0.40

Snacks

0.40

FXML

0.39

 toekomst

0.39

 geçmiş

0.39

 wüns

0.38

Activations Density 0.003%

occurrences of programming-related terms and queries

filter expressions

No Comments

No Known Activations