INDEX

Explanations

references to people and legal entities within legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

-0.88

windowFixed

-0.67

ंदीखरीदारी

-0.61

EndGlobalSection

-0.57

czes

-0.57

Hauptartikel

-0.56

最快更新

-0.55

 оригіналу

-0.55

 tromper

-0.54

 rynku

-0.54

POSITIVE LOGITS

 entities

0.76

 persons

0.68

anyone

0.63

 anyone

0.62

 anybody

0.62

RenderAtEndOf

0.61

Anybody

0.61

 things

0.61

 entity

0.61

 ANYONE

0.60

Activations Density 1.039%

references to people and legal entities within legal contexts

No Comments

No Known Activations