INDEX

Explanations

elements related to data structures and their properties

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

programming variable names

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

OGND

-0.59

 Paglinawan

-0.54

новниш

-0.47

>{@

-0.46

XmlAccessType

-0.45

ंदीखरीदारी

-0.42

хьтан

-0.42

 createContext

-0.41

Vidite

-0.41

eqn

-0.38

POSITIVE LOGITS

ouchable

0.44

apatalk

0.43

vertreter

0.43

 infil

0.42

 Affidavit

0.41

 pedro

0.41

pecker

0.41

webElementXpaths

0.40

inhardt

0.40

 ComVisible

0.40

Activations Density 0.076%

elements related to data structures and their properties

programming variable names

No Comments

No Known Activations