INDEX

Explanations

mathematical expressions and notations related to distributions and modeling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

 autorytatywna

-0.80

quelize

-0.58

 ModelExpression

-0.49

bootstrapcdn

-0.47

tanleria

-0.47

DMETHOD

-0.47

tvguidetime

-0.44

 bezeichneter

-0.43

IconModule

-0.43

BagLayout

-0.43

POSITIVE LOGITS

 inicial

0.60

 initial

0.59

初始

0.57

Initial

0.56

 Initial

0.55

initial

0.54

 iniciales

0.50

 초기

0.50

setInitial

0.49

 iniz

0.48

Activations Density 0.858%

mathematical expressions and notations related to distributions and modeling

No Comments

No Known Activations