INDEX

Explanations

instances of numerical values or mathematical expressions

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

numbers and years

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

copg

-0.54

@[+][

-0.52

artifactId

-0.51

فایل‌لار

-0.49

ThroughAttribute

-0.49

djangoproject

-0.48

aphthalene

-0.47

دانشنامهٔ

-0.47

 gleichen

-0.47

XmlSchema

-0.47

POSITIVE LOGITS

########.

0.97

:+:

0.69

libft

0.57

 ویکی‌پدیا

0.38

+#+

0.37

 étudiant

0.36

 Students

0.36

 Student

0.36

 BITS

0.35

 незавершена

0.34

Activations Density 0.002%

instances of numerical values or mathematical expressions

numbers and years

No Comments

No Known Activations