INDEX

Explanations

terms related to production and organizational processes in research contexts

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

formats and classifications

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

LookAnd

-0.54

 aidant

-0.46

SequentialGroup

-0.46

 intptr

-0.45

 thiệu

-0.45

Kaynakça

-0.45

 հղումներ

-0.44

IndentedString

-0.44

Przypisy

-0.44

Примітки

-0.43

POSITIVE LOGITS

principalColumn

0.49

NameInMap

0.33

ackerel

0.33

 дописавши

0.33

 getItemId

0.32

Configurer

0.32

RenderAtEndOf

0.32

سام

0.32

andowski

0.31

marshaller

0.31

Activations Density 0.060%

terms related to production and organizational processes in research contexts

formats and classifications

No Comments

No Known Activations