INDEX

Explanations

named entities and associated terms related to legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Smit

-0.77

 resourceCulture

-0.77

 Nestor

-0.76

FormTagHelper

-0.75

modelBuilder

-0.73

 Bioaccumulative

-0.71

ękuję

-0.70

okovic

-0.69

Zia

-0.69

 flèche

-0.68

POSITIVE LOGITS

 Angular

0.83

Angular

0.80

 Kanz

0.79

 Baller

0.79

 Chamb

0.78

 localVar

0.78

 Cristi

0.78

 Edwards

0.76

 Kuri

0.74

Kuri

0.73

Activations Density 1.948%

named entities and associated terms related to legal contexts

No Comments

No Known Activations