INDEX

Explanations

elements related to legal terminology and entities

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

 Económica

-0.49

errHandler

-0.44

 electrónica

-0.43

 tecnológica

-0.38

 usein

-0.36

migrationBuilder

-0.36

 typically

-0.35

 kullanılır

-0.35

 estés

-0.35

 dép

-0.35

POSITIVE LOGITS

parsedMessage

0.59



0.54

KURZBESCHREIBUNG

0.54

RegressionTest

0.54

 CreateTagHelper

0.53

Dtor

0.53

 autorytatywna

0.52

⟬

0.52

utilisons

0.52

 knex

0.51

Activations Density 1.298%

elements related to legal terminology and entities

No Comments

No Known Activations