INDEX

Explanations

code related to quiz and polling functionality

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

quiz questions answers

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

ArrowToggle

-0.71

AddTagHelper

-0.66

Personendaten

-0.63

AndEndTag

-0.59

EndGlobalSection

-0.59

يميديا

-0.57

featureID

-0.53

AddHtmlAttribute

-0.53

 surla

-0.53

 NSCoder

-0.52

POSITIVE LOGITS

 questions

1.00

 question

0.98

 quiz

0.96

 Question

0.94

 answers

0.83

question

0.82

 Quiz

0.81

Question

0.80

 Questions

0.79

 answer

0.75

Activations Density 0.042%

code related to quiz and polling functionality

quiz questions answers

No Comments

No Known Activations