INDEX

Explanations

programming-related syntax and definitions

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

Code snippets or game development code

np_acts-logits-general · gemini-2.0-flash

setting, adding, displaying graphics

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

########.

-0.60

 propOrder

-0.53

viewDidLoad

-0.53

inheit

-0.50

 Coordinates

-0.50

 getInstance

-0.50

 Tetrahedron

-0.49

 coordinates

-0.49

 concor

-0.49

 Evanston

-0.48

POSITIVE LOGITS

 BrowserModule

0.67

Xna

0.60

 Friar

0.57

ImageContext

0.57

bcryptjs

0.55

 FetchType

0.54

theoremstyle

0.52

writeFieldEnd

0.51



0.51

 wireType

0.50

Activations Density 0.073%

programming-related syntax and definitions

Code snippets or game development code

setting, adding, displaying graphics

No Comments

No Known Activations