INDEX

Explanations

markers indicating quoted speech or dialogue

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

<start_of_turn>user

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

TypedDataSet

-0.56

ValueStyle

-0.55

DockStyle

-0.51

⟬

-0.44

WEBPACK

-0.41

ThroughAttribute

-0.41

ngdoc

-0.40

AutoresizingMask

-0.40

ftagPool

-0.39

RegressionTest

-0.39

POSITIVE LOGITS

 ویکی‌پدیا

0.95

 Italijanski

0.58

 okuyayım

0.56

évaluateur

0.55

Espèce

0.54

KURZBESCHREIBUNG

0.48

 ujednoznacz

0.46

 trône

0.45

 nieco

0.45

 المعيارى

0.45

Activations Density 0.000%

markers indicating quoted speech or dialogue

<start_of_turn>user

No Comments

No Known Activations