INDEX

Explanations

specific identifiers or variables within a technical context, likely related to programming or data structures

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

NamedQueries

-0.38

 AssemblyProduct

-0.33

fontName

-0.32

 forState

-0.29

 shop

-0.29

///</

-0.29

 daarna

-0.29

 basic

-0.28

stånd

-0.28

EventQueue

-0.28

POSITIVE LOGITS

StoryboardSegue

0.65

 purpoſe

0.63

DeleteBehavior

0.59

UserScript

0.59

 greateſt

0.57

tagHelperRunner

0.54

OGND

0.53

 disambiguazione

0.52

AddTagHelper

0.51

 referrerpolicy

0.51

Activations Density 1.242%

specific identifiers or variables within a technical context, likely related to programming or data structures

No Comments

No Known Activations