INDEX

Explanations

programming-related keywords and structures

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

XML namespaces and attributes

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

XmlRootElement

-0.59

expandindo

-0.58

 Италијани

-0.57

UserScript

-0.56

CppMethod

-0.56

Rüyada

-0.56

SBATCH

-0.55

 Audiodateien

-0.55

AndroidJUnit

-0.53

 виправивши

-0.51

POSITIVE LOGITS

Билгалдахарш

0.37

 సౌకర్య

0.36

 nahilalakip

0.35

utilisons

0.35

ATELY

0.33

QRect

0.33

<%@

0.32

AxisAlignment

0.32

</>

0.32

ToBounds

0.32

Activations Density 0.013%

programming-related keywords and structures

XML namespaces and attributes

No Comments

No Known Activations