INDEX

Explanations

indicators of structure or formatting in coding contexts

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

elements related to graphical user interface (GUI) layout and attributes

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

rod lever

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

Архівовано

-0.65

Portail

-0.65

<eos>

-0.63

 tartalomajánló

-0.62

AndEndTag

-0.61

InitVars

-0.61

 estekak

-0.59

twimg

-0.58

 Мексичка

-0.57

CrossRef

-0.55

POSITIVE LOGITS

tagHelperRunner

0.59

 بيها

0.56

dersfield

0.55

pertory

0.50

akterysty

0.49

EXPECTED

0.48

 Fris

0.47

aughty

0.46

 للمعارف

0.45

 artificiales

0.45

Activations Density 0.007%

indicators of structure or formatting in coding contexts

elements related to graphical user interface (GUI) layout and attributes

rod lever

No Comments

No Known Activations