INDEX

Explanations

terms and references related to programming languages and frameworks, particularly those used in web development

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

Code-related tokens, often after punctuation

np_acts-logits-general · gemini-2.0-flash

words after symbols or 'ng'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 typelib

-0.77

apimachinery

-0.68

GraphicsUnit

-0.65

GOTREF

-0.65

ControllerAdvice

-0.63

 dieß

-0.63

ExecuteReader

-0.63

 AssemblyCompany

-0.62

canActivate

-0.62

ValueStyle

-0.62

POSITIVE LOGITS

urably

0.65

 Rest

0.55

THY

0.53

simple

0.49

 rest

0.48

Rest

0.48

ximity

0.47

easy

0.47

 Easy

0.47

кра

0.47

Activations Density 0.088%

terms and references related to programming languages and frameworks, particularly those used in web development

Code-related tokens, often after punctuation

words after symbols or 'ng'

No Comments

No Known Activations