INDEX

Explanations

mentions of JAR files and related library references

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

jar assembly dll

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

DotNetBar

-0.48

AndEndTag

-0.47

RuleContext

-0.45

:+:

-0.43

ScopeManager

-0.40

 conduc

-0.39

Scalars

-0.38

formik

-0.38

ValueGenerated

-0.37

ibatis

-0.36

POSITIVE LOGITS

TypedDataSet

0.55

principalColumn

0.45

脚注の使い方

0.45

ppelin

0.44

CPtr

0.43

 AssemblyCompany

0.42

 imageNamed

0.41

 Schiffe

0.41

 boules

0.41

ThroughAttribute

0.40

Activations Density 0.026%

mentions of JAR files and related library references

jar assembly dll

No Comments

No Known Activations