INDEX

Explanations

code-related keywords and functions in programming documentation

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

conditions or checks in programming related to null values and file handling

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

per month

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

 فريبيس

-0.85

 виправивши

-0.70

 AssemblyTitle

-0.67

 initComponents

-0.66

RUnlock

-0.59

 Signalez

-0.57

elemField

-0.56

 متعلقه

-0.55

 resourceCulture

-0.55

 transfieras

-0.55

POSITIVE LOGITS

脚注の使い方

0.70

PRWEB

0.66

 précédents

0.62

 Stuff

0.60

 originais

0.59

 civile

0.59

 femei

0.56

ndice

0.55

 personnalisés

0.54

 acredita

0.53

Activations Density 0.011%

code-related keywords and functions in programming documentation

conditions or checks in programming related to null values and file handling

per month

No Comments

No Known Activations