INDEX

Explanations

references to the React library and its components

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

Reactjs code

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

дент

-0.38

 înc

-0.35

 fermo

-0.35

 betyd

-0.34

 giudi

-0.32

 rând

-0.31

setObjectName

-0.31

ýš

-0.31

 abband

-0.31

 kautta

-0.31

POSITIVE LOGITS

react

0.99

 initComponents

0.86

 React

0.80

REACT

0.76

 createState

0.75

 REACT

0.73

 react

0.72

IContainer

0.70

React

0.68

 jsPsych

0.67

Activations Density 0.001%

references to the React library and its components

Reactjs code

No Comments

No Known Activations