INDEX

Explanations

structure markers and annotations in documents

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Key components, lists

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

Negative Logits

RegistryLite

-0.74

OGND

-0.68

CloseOperation

-0.61

SourceChecksum

-0.57

writeFieldEnd

-0.57

Geografía

-0.54

 تكبرها

-0.54

 transfieras

-0.54

 Италијани

-0.53

OrNil

-0.53

POSITIVE LOGITS

 feit

0.39

 stránka

0.36

etc

0.35

 faptul

0.34

RTCK

0.33

generally

0.33

banden

0.33

simple

0.32

추

0.32

 것이다

0.32

Activations Density 0.019%

structure markers and annotations in documents

Key components, lists

No Known Activations