INDEX

Explanations

legal terminology and phrases related to court rulings and legal proceedings

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

followed by "the"

np_acts-logits-general · gemini-2.0-flash

granted or denied

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

igshid

-0.74

出版年

-0.71

 CURIAM

-0.69

Hauptartikel

-0.64

NameInMap

-0.63

antMatchers

-0.60

inama

-0.56

PYX

-0.56

 derer

-0.54

ticles

-0.53

POSITIVE LOGITS

 such

0.71

ValueStyle

0.67

 semejante

0.65

 ostavi

0.58

Such

0.58

such

0.57

 traccia

0.54

medim

0.54

gemeester

0.53

ดัง

0.53

Activations Density 0.649%

legal terminology and phrases related to court rulings and legal proceedings

followed by "the"

granted or denied

No Comments

No Known Activations