INDEX

Explanations

references to additional information or reading material

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

reading more, continue reading

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

 ModelExpression

-0.56

+:+

-0.51

 JpaRepository

-0.49

XmlAccessorType

-0.45

Chham

-0.45

AnchorTagHelper

-0.45

 Formato

-0.43

 způso

-0.42

 vuur

-0.41

 StringTokenizer

-0.41

POSITIVE LOGITS

səhifə

0.63

 виправивши

0.56

 незавершена

0.55

 Numerade

0.50

 tartalomajánló

0.48

RTLD

0.48

 autorytatywna

0.45

 INTERESAR

0.45

 EconPapers

0.45

VIAF

0.44

Activations Density 0.000%

references to additional information or reading material

reading more, continue reading

No Comments

No Known Activations