INDEX

Explanations

legal terminology and concepts related to court rulings and appeals

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 greateſt

-0.82

+#+#

-0.81

 Anſ

-0.79

 Monfieur

-0.78

 myſelf

-0.76

 Theſe

-0.75

Efq

-0.74

 protoimpl

-0.73

parsedMessage

-0.71

følgelig

-0.71

POSITIVE LOGITS

 unless

2.21

unless

1.85

Unless

1.70

 Unless

1.66

除非

1.25

 without

1.13

 إلا

1.09

 kecuali

1.06

 except

1.05

 until

0.95

Activations Density 0.452%

legal terminology and concepts related to court rulings and appeals

No Comments

No Known Activations