INDEX

Explanations

references to specific concepts or keywords related to academic or formal documentation

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

Follows non-English language words

np_acts-logits-general · gemini-2.0-flash

zur Förderung

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

thinkable

-0.57

didSet

-0.57

odi

-0.56

jdt

-0.56

 StatelessWidget

-0.55

nestjs

-0.55

 CGRect

-0.54

BorderLayout

-0.54

 intervened

-0.54

tph

-0.53

POSITIVE LOGITS

 ModelExpression

0.58

cloudfront

0.50

dymyr

0.48

XMLSchema

0.46

fromnode

0.45

 Stra

0.45

du

0.44

 stra

0.42

لينا

0.42

хьтан

0.42

Activations Density 0.046%

references to specific concepts or keywords related to academic or formal documentation

Follows non-English language words

zur Förderung

No Comments

No Known Activations