INDEX

Explanations

references to specific quantities or attributes associated with health-related conditions

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

 שוליים

-0.90

 CreateTagHelper

-0.84

AnchorStyles

-0.81

fillType

-0.77

adə

-0.75

SharedDtor

-0.75

 saites

-0.74

 estekak

-0.73

StoryboardSegue

-0.70

новништво

-0.69

POSITIVE LOGITS

Chapter

0.77

 Chapter

0.74

 chapter

0.63

↵↵

0.61

chapter

0.58

He

0.57

As

0.55

↵

0.54

 Chapitre

0.53

 geslacht

0.53

Activations Density 0.032%

references to specific quantities or attributes associated with health-related conditions

No Comments

No Known Activations