INDEX

Explanations

code snippets and programming-related syntax

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

python programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

OrBuilder

-0.56

exitRule

-0.53

WireFormatLite

-0.53

 lenker

-0.49

testify

-0.49

出版年

-0.48

webElementXpaths

-0.47

Šaltiniai

-0.45

yntaxException

-0.44

 disambiguazione

-0.43

POSITIVE LOGITS

stonia

0.44

 Behr

0.44

 lære

0.41

rceil

0.40

 sáng

0.40

BeforeMethod

0.40

mag

0.40

lück

0.39

 AssemblyCompany

0.39

ंदीखरीदारी

0.39

Activations Density 0.060%

code snippets and programming-related syntax

python programming constructs

No Comments

No Known Activations