INDEX

Explanations

technical terms related to programming and software development

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

Followed by parentheses

np_acts-logits-general · gemini-2.0-flash

system

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.83

Хьажоргаш

-0.79

AddHtmlAttribute

-0.75

apunov

-0.72

Autoritní

-0.71

 cherchés

-0.71

 تضيفلها

-0.70

 nakalista

-0.70

aarrggbb

-0.69

POSITIVE LOGITS

 System

0.94

System

0.83

 system

0.82

 Syst

0.65

system

0.64

Syst

0.61

 sistem

0.60

 SYSTEM

0.60

 Systems

0.58

システム

0.57

Activations Density 0.232%

technical terms related to programming and software development

Followed by parentheses

system

No Comments

No Known Activations