INDEX

Explanations

references to specific database or programming elements, particularly "eb" codes and "phase" terminology

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

mut

-0.51

LLocation

-0.48

 getWidth

-0.46

 thousand

-0.44

FunctionType

-0.43

 indiana

-0.43

 ence

-0.42

 Kung

-0.42

 press

-0.42

 Huntington

-0.42

POSITIVE LOGITS

хьтан

0.68

 belleza

0.68

lewati

0.63

 Biôgrafia

0.63

Pie

0.62

 idéale

0.60

 beauté

0.60

 beleza

0.59

曖昧さ回避

0.59

Personensuche

0.59

Activations Density 0.200%

references to specific database or programming elements, particularly "eb" codes and "phase" terminology

No Known Activations