INDEX

Explanations

programming-related terms, specifically related to classes and functions

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

Kotlin code and related keywords

np_acts-logits-general · gemini-2.0-flash

kotlin keywords (`val`, `var`, `fun`)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 pinulongan

-0.84

omotor

-0.70

enumii

-0.70

webElementXpaths

-0.69

AnchorStyles

-0.68

GraphicsUnit

-0.65

crollView

-0.63

хьтан

-0.63

Билгалдахарш

-0.63

Referencer

-0.61

POSITIVE LOGITS

val

1.02

fun

1.02

val

0.98

fun

0.98

var

0.60

lateinit

0.60

Fun

0.60

FUN

0.59

FUN

0.59

companion

0.58

Activations Density 0.084%

programming-related terms, specifically related to classes and functions

Kotlin code and related keywords

kotlin keywords (`val`, `var`, `fun`)

No Comments

No Known Activations