INDEX

Explanations

terms related to copyright and licensing

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

attribution license

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

 Taktlose

-0.45

delwed

-0.39

endphp

-0.38

Où

-0.38

 GetEnumerator

-0.37

Intial

-0.37

rungsseite

-0.36

 Schluß

-0.36

 Bewußt

-0.36

ļas

-0.36

POSITIVE LOGITS

 Attribution

0.59

addCriterion

0.48

 BoxFit

0.48

inWeight

0.45

ıntı

0.45

Rigidbody

0.44

AsUp

0.44

Attribution

0.44

 attribution

0.44

 Shade

0.44

Activations Density 0.001%

terms related to copyright and licensing

attribution license

No Comments

No Known Activations