INDEX

Explanations

elements related to legal or judicial terminology

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

principalColumn

-0.49

OCCURRED

-0.48

WireFormatLite

-0.47

 propOrder

-0.47

autorest

-0.46

 pinulongan

-0.44

حياته

-0.42

invokeLater

-0.41

makeConstraints

-0.41

 hopeful

-0.39

POSITIVE LOGITS

enumii

0.48

enumi

0.47

 NgModule

0.45

føl

0.42

ſelves

0.42

 nytt

0.42

CopyWith

0.41

épendance

0.41

npmjs

0.41

Simpli

0.41

Activations Density 0.117%

elements related to legal or judicial terminology

No Comments

No Known Activations