INDEX

Explanations

references to numerical data, particularly involving counts or identifiers

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 @ 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

msgTypes

-0.73

principalColumn

-0.50

❉

-0.50

:✨

-0.49

enumii

-0.49

 protoimpl

-0.48

findpost

-0.47

OGND

-0.47

"><?=

-0.46

NameInMap

-0.44

POSITIVE LOGITS

Izvori

0.47

Życiorys

0.43

ConstraintMaker

0.41

Referencie

0.38

AccessFile

0.35

AutoField

0.35

بوابة

0.35

subplots

0.34

mapStateToProps

0.34

instancetype

0.34

Activations Density 0.013%

references to numerical data, particularly involving counts or identifiers

codes and identifiers

No Comments

No Known Activations