INDEX

Explanations

Java package import statements from the Apache Commons libraries

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

apache commons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

parsedMessage

-0.63

ngdoc

-0.52

usermodel

-0.48

principalColumn

-0.47

bcryptjs

-0.47

RTSC

-0.46

awaiter

-0.46

adaptiveStyles

-0.45



-0.45

期刊论文

-0.45

POSITIVE LOGITS

 Administrativna

0.52

springframework

0.43

apache

0.42

imgs

0.41

Hdr

0.40

 Robert

0.40

 Theodore

0.39

 REPUBLIC

0.39

 Dominican

0.38

 Cindy

0.38

Activations Density 0.026%

Java package import statements from the Apache Commons libraries

apache commons

No Comments

No Known Activations