INDEX

Explanations

punctuation marks and numeric references in the text

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

citations and references

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

 Italijani

-0.65

SharedDtor

-0.55

IndentedString

-0.52

 HasFactory

-0.48

 Wikimedijinoj

-0.46

 Roskov

-0.45

reportWebVitals

-0.45

Vidite

-0.45

iNdEx

-0.44

 Normdatei

-0.43

POSITIVE LOGITS

BASEPATH

0.40

felves

0.40

fromnode

0.39

 समीक्षक

0.38

TagNumber

0.38

fjspx

0.38

 recevrez

0.38

sidemargin

0.37

同期

0.37

Activations Density 0.013%

punctuation marks and numeric references in the text

citations and references

No Comments

No Known Activations