INDEX

Explanations

identifiers related to devices and systems in technical contexts

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

codes and identifiers

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

ReusableCell

-0.66

ValueStyle

-0.65

endphp

-0.59

RegressionTest

-0.59

 BoxFit

-0.54

Efq

-0.51

 imageNamed

-0.50

참고

-0.48

IsMutable

-0.48

 zove

-0.46

POSITIVE LOGITS

VIAF

0.51

 VIAF

0.49

 LCCN

0.47

InteropServices

0.42

 ISNI

0.41

 EconPapers

0.40

 συγ

0.39

nanoTime

0.39

Identyfik

0.38

lanması

0.36

Activations Density 0.050%

identifiers related to devices and systems in technical contexts

codes and identifiers

No Comments

No Known Activations