INDEX

Explanations

code-related commands for manipulating a canvas or graphics context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

 disambiguazione

-0.65

 COMERC

-0.62

werd

-0.61

 TAMBIÉN

-0.58

aunt

-0.58

 estekak

-0.57

CppMethod

-0.56

 Ephe

-0.56

 TÉCN

-0.56

iNdEx

-0.56

POSITIVE LOGITS

 հղումներ

0.55

ELTS

0.51

تفصیلات

0.49

はじめに

0.48

 saites

0.47

EndProject

0.46

translate

0.45

save

0.44

 ellipse

0.43

AccessorTable

0.43

Activations Density 0.140%

code-related commands for manipulating a canvas or graphics context

No Comments

No Known Activations