INDEX

Explanations

indicators of system status or error

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

technical terms and punctuation

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

 Consultez

-0.40

 lisäksi

-0.38

 generaciones

-0.38

 stabilité

-0.38

Literatuur

-0.37

audiovisuel

-0.37

 yürü

-0.36

 gümüş

-0.35

 financeira

-0.35

PMailer

-0.35

POSITIVE LOGITS

tvguidetime

0.58

 ostavi

0.52

NUMX

0.52

ChildScrollView

0.51

0.50

-------

0.49

 referrerpolicy

0.48

 مشين

0.48

 suspen

0.48

ValueStyle

0.47

Activations Density 0.135%

indicators of system status or error

technical terms and punctuation

No Comments

No Known Activations