INDEX

Explanations

special characters and formatting in text

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

identifier

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

Gön

-0.46

Архівовано

-0.43

 JpaRepository

-0.42

 encouraging

-0.42

expliquer

-0.41

 onPause

-0.41

 Liner

-0.41

setCellStyle

-0.40

]=>

-0.40

?>>

-0.40

POSITIVE LOGITS

 identifier

0.75

WebElementEntity

0.73

identifier

0.70

 identifiers

0.69

 Identifier

0.59

ScopeManager

0.56

 AssemblyTitle

0.53

identifiers

0.52

 identitas

0.52

Identifier

0.52

Activations Density 0.000%

special characters and formatting in text

identifier

No Comments

No Known Activations