INDEX

Explanations

references to legal case citations and court rulings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

存于互联网档案馆

-0.62

fhir

-0.61

mmation

-0.57

standard

-0.55

labus

-0.54

 متعلقه

-0.53

ActionMode

-0.52

 STANDARD

-0.51

دانشنامهٔ

-0.50

stache

-0.49

POSITIVE LOGITS

 Parliament

0.83

#+#

0.76

 parliament

0.73

 court

0.71

 Legislature

0.71

 Court

0.69

 courts

0.68

 Senate

0.66

議院

0.66

 legislature

0.61

Activations Density 0.791%

references to legal case citations and court rulings

No Comments

No Known Activations