INDEX

Explanations

references to the name "Ka" and its variations in different contexts

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

starting with "Ka"

np_acts-logits-general · gemini-2.0-flash

Kai or ka_in prefixes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 /\.(

-0.58

 resultCode

-0.56

 raising

-0.48

veland

-0.48

nature

-0.47

 Code

-0.47

 disallowed

-0.47

 leksikon

-0.46

drawString

-0.46

 برانيه

-0.45

POSITIVE LOGITS

 <>",

0.72

InitVars

0.65

RegistryLite

0.63

tagHelperRunner

0.63

 <<<<<<<<<<<<<<

0.63

NewUrlParser

0.62

 disambiguazione

0.61

parsedMessage

0.60

 виправивши

0.60

LookAnd

0.59

Activations Density 0.067%

references to the name "Ka" and its variations in different contexts

starting with "Ka"

Kai or ka_in prefixes

No Comments

No Known Activations