INDEX

Explanations

references to court proceedings and judicial contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

rungsseite

-0.95

iyle

-0.68

ismen

-0.66

 Pedersen

-0.66

 paja

-0.65

isal

-0.65

 vitale

-0.64

hile

-0.64

 AssemblyTitle

-0.63

dă

-0.63

POSITIVE LOGITS

 Court

1.54

 Courts

1.39

 COURT

1.36

 court

1.27

Court

1.27

 courts

1.26

COURT

1.22

 COUR

1.21

courts

1.20

court

1.19

Activations Density 0.118%

references to court proceedings and judicial contexts

No Comments

No Known Activations