INDEX

Explanations

code-related terms and constructs in programming or data structure contexts

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

references to machine learning or data processing components in code

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

spacy nlp models and simulations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

اذ

-0.46

Ử

-0.45

 chances

-0.45

 بخ

-0.44

big

-0.43

jspx

-0.43

VisualStudio

-0.42

sho

-0.42

 MediaQuery

-0.42

 authentic

-0.42

POSITIVE LOGITS

 CreateTagHelper

1.01

OGND

0.83

 تانيه

0.81

 kasarigan

0.80

DockStyle

0.78

NameInMap

0.76

sidemargin

0.75

 >=",

0.74

Referencie

0.74

 ReactDOM

0.73

Activations Density 0.015%

code-related terms and constructs in programming or data structure contexts

references to machine learning or data processing components in code

spacy nlp models and simulations

No Comments

No Known Activations