INDEX

Explanations

indications of structure and organization in programming contexts

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

Non-English or code-related text

np_acts-logits-general · gemini-2.0-flash

code and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

AutoScale

-0.74

!")

-0.66

"):

-0.66

")

-0.65

"){

-0.61

uvres

-0.59

")){

-0.59

 تضيفلها

-0.58

 }}$}

-0.58

ftance

-0.58

POSITIVE LOGITS

 kasarigan

0.77

Билгалдахарш

0.77

omitempty

0.69

 muualla

0.67

 Wallflower

0.65

 disponibilités

0.62

orianCalendar

0.61

 createContext

0.61

">//

0.60

ագրություններ

0.60

Activations Density 0.571%

indications of structure and organization in programming contexts

Non-English or code-related text

code and technical terms

No Comments

No Known Activations