INDEX

Explanations

elements related to quizzes and question formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bootstrapcdn

-0.95

EDEFAULT

-0.88

?}",

-0.63

 }}}{

-0.61

 виправивши

-0.59

 فريبيس

-0.59

cyklopedia

-0.59

WriteBarrier

-0.58

 ddelweddau

-0.58

awaiter

-0.58

POSITIVE LOGITS

 puzzle

0.73

 challenge

0.72

 puzzles

0.65

 challenges

0.62

 tasks

0.60

 completion

0.59

 Puzzle

0.59

 laby

0.58

 boss

0.58

 challenging

0.57

Activations Density 0.290%

elements related to quizzes and question formats

No Comments

No Known Activations