INDEX

Explanations

elements of programming or coding syntax

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

change css

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

export

-0.42

mità

-0.40

 export

-0.39

ashqai

-0.37

TokenNameLPAREN

-0.36

 cirrhosis

-0.36

RESUMO

-0.35

CCESS

-0.35

 Infór

-0.35

 Highlanders

-0.35

POSITIVE LOGITS

 EconPapers

0.68

EndGlobalSection

0.63

TagMode

0.61

0.56

+:+

0.54

Tikang

0.53

UserScript

0.50

contentLoaded

0.50

 surla

0.50

LookAnd

0.49

Activations Density 0.012%

elements of programming or coding syntax

change css

No Comments

No Known Activations