INDEX

Explanations

terminology and structures related to legal and transactional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 myſelf

-0.68

Efq

-0.62

 Audiodateien

-0.62

 itſelf

-0.57

saraba

-0.57

 themſelves

-0.57

 fometimes

-0.55

 himſelf

-0.54

 uſed

-0.52

atiker

-0.50

POSITIVE LOGITS

 estekak

0.65

Personendaten

0.59

 <=",

0.52

 оригіналу

0.51

 noDo

0.51

といけない

0.50

 spéciales

0.49

הם

0.49

 rechange

0.49

期刊论文

0.49

Activations Density 2.240%

terminology and structures related to legal and transactional contexts

No Comments

No Known Activations