INDEX

Explanations

mathematical notation and symbols used in equations

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

appearing with asterisks

np_acts-logits-general · gemini-2.0-flash

health and scientific research

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

хьтан

-0.53

kep

-0.48

manian

-0.45

-0.44

-0.43

blo

-0.43

POSITIVE LOGITS

ViewFeatures

0.80

 snippetHide

0.77

WebElementEntity

0.74

 الحره

0.74

 betweenstory

0.72

ArgsConstructor

0.72

providedIn

0.69

GenerationType

0.66

');

0.65

ModelAdmin

0.64

Activations Density 0.806%

mathematical notation and symbols used in equations

appearing with asterisks

health and scientific research

No Comments

No Known Activations