INDEX

Explanations

numerical data, particularly related to measurements and percentages

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

Numbers in lists

np_acts-logits-general · gemini-2.0-flash

numerical lists or data

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

 termes

-0.47

락

-0.45

 termino

-0.45

ән

-0.44

 Placebo

-0.44

mû

-0.41

[++

-0.41

SerializedSize

-0.41

Citiți

-0.41

audi

-0.41

POSITIVE LOGITS

 Chwiliwch

0.83

 MotionEvent

0.70

istoitu

0.68

RenderAtEndOf

0.67

xodo

0.60

ductory

0.59

 odkazy

0.59

UnifiedTopology

0.58

 Dostupné

0.57

odorant

0.57

Activations Density 0.283%

numerical data, particularly related to measurements and percentages

Numbers in lists

numerical lists or data

No Comments

No Known Activations