INDEX

Explanations

permissions or enabling statements

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

allow reference

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

<?

-0.50

TypedDataSet

-0.46

ThroughAttribute

-0.45

:=

-0.43

 Waray

-0.43

 künftig

-0.43

 Мексичка

-0.42

ppuden

-0.42

最快更新

-0.41

POSITIVE LOGITS

allowNull

3.16

HomeAsUpEnabled

0.64

tangentMode

0.58

 DataTypes

0.54

sizeCache

0.51

 Allow

0.50

requireNonNull

0.49

GIVEREF

0.48

AllowUser

0.47

toThrow

0.46

Activations Density 0.000%

permissions or enabling statements

allow reference

No Comments

No Known Activations