INDEX

Explanations

annotations or metadata markings within code

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

 isolé

-0.65

 stratégique

-0.64

 flèche

-0.60

 régionale

-0.60

 goutte

-0.58

 épais

-0.57

 sauvages

-0.56

 habet

-0.55

 barbati

-0.54

 aislada

-0.53

POSITIVE LOGITS

TagMode

0.72

 المعيارى

0.71

 resourceCulture

0.69

 GenerationType

0.67

version

0.66

author

0.66

 JpaRepository

0.65

 disambiguazione

0.65

WithIOException

0.64

 indisponible

0.63

Activations Density 0.044%

annotations or metadata markings within code

No Comments

No Known Activations