INDEX

Explanations

references to legal cases and judicial opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

monials

-0.50

autorest

-0.46

спита

-0.41

 JpaRepository

-0.40

enderror

-0.39

 DPRD

-0.39

contentLoaded

-0.39

WithIdentifier

-0.39

 éprou

-0.38

]=>

-0.38

POSITIVE LOGITS

 justices

1.06

 Justices

1.03

 Supreme

1.02

 Justice

0.97

 SCOT

0.88

Justice

0.86

Supreme

0.86

 SUPREME

0.81

 justice

0.79

Jus

0.76

Activations Density 2.111%

references to legal cases and judicial opinions

No Comments

No Known Activations