INDEX

Explanations

keywords and phrases related to web content and its structure

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

URLs and code snippets

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

 препратки

-0.57

IntoConstraints

-0.53

 مرئيه

-0.53

ReusableCell

-0.47

 GenerationType

-0.46

 ब्रेकडाउन

-0.45

 المعيارى

-0.43

 NSCoder

-0.43

 GetEnumerator

-0.43

 AssemblyTitle

-0.40

POSITIVE LOGITS

tagHelperRunner

0.48

uxxxx

0.48

Train

0.45

 Numerade

0.42

 Cupertino

0.40

Fris

0.40

bcryptjs

0.39

Flip

0.38

lujah

0.38

 hygge

0.37

Activations Density 0.001%

keywords and phrases related to web content and its structure

URLs and code snippets

No Comments

No Known Activations