INDEX

Explanations

code-related concepts, such as definitions of classes, variables, and method structures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

balleur

-0.57

 artigian

-0.52

UNSIGNED

-0.51

êque

-0.51

devamını

-0.48

shields

-0.48

gup

-0.47

 виправивши

-0.47

 HasFactory

-0.46

roblast

-0.46

POSITIVE LOGITS

 defaultstate

0.76

脚注の使い方

0.68

///</

0.67

:✨

0.65

InitVars

0.62

 StatefulWidget

0.62

PerformLayout

0.62

 nahilalakip

0.61

 dAtA

0.61

 onAnimation

0.56

Activations Density 0.128%

code-related concepts, such as definitions of classes, variables, and method structures

No Comments

No Known Activations