INDEX

Explanations

code definitions and function declarations in programming languages

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

Code snippets and programming-related terms

np_acts-logits-general · gemini-2.0-flash

solve programming problems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 ujednoznacz

-0.65

 الحره

-0.64

PreferredItem

-0.59

TableBody

-0.56

formik

-0.55

 وتسجيلات

-0.55

 Aung

-0.54

</caption>

-0.54

 numberOfRows

-0.53

webElementXpaths

-0.52

POSITIVE LOGITS

ll

0.57

 solve

0.56

freopen

0.51

LL

0.51

ans

0.49

ans

0.49

solve

0.49

WebMethod

0.49

 solves

0.48

Ans

0.47

Activations Density 0.121%

code definitions and function declarations in programming languages

Code snippets and programming-related terms

solve programming problems

No Comments

No Known Activations