INDEX

Explanations

programming languages or data structures in technical documentation

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

units of measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 незавершена

-0.77

 Signalez

-0.63

 للمعارف

-0.62

verwijspagina

-0.60

￳

-0.59

 समीक्षाओं

-0.58

 AttributeSet

-0.57

 snippetHide

-0.55

BeginContext

-0.54

ロウィン

-0.54

POSITIVE LOGITS

AutoField

0.46

feinander

0.33

ModelSerializer

0.31

GTCX

0.31

Бележки

0.31

invokeLater

0.31

addPreferredGap

0.31

ataires

0.30

ダー

0.30

Посилання

0.29

Activations Density 0.079%

programming languages or data structures in technical documentation

units of measurement

No Comments

No Known Activations