INDEX

Explanations

occurrences of legal terminology and references to legal proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

-0.30

 juntas

-0.30

Their

-0.30

-0.29

 Union

-0.27

namespace

-0.27

Our

-0.27

 mutually

-0.27

<h6>

-0.26

 priorité

-0.26

POSITIVE LOGITS

 himself

1.03

himself

0.98

 himſelf

0.72

 Himself

0.67

 herself

0.66

herself

0.64

XMLSchema

0.63

 चाहता

0.63

 EconPapers

0.62

+#+

0.61

Activations Density 0.695%

occurrences of legal terminology and references to legal proceedings

No Comments

No Known Activations