INDEX

Explanations

structured legal or administrative content related to entities and documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Tirana

-0.63

 Igbo

-0.61

 للاسماء

-0.61

mybatisplus

-0.60

 Kuba

-0.59

 يتيمه

-0.59

 Slovak

-0.58

 phospho

-0.56

 Dhaka

-0.56

 tornado

-0.56

POSITIVE LOGITS

 California

1.99

California

1.86

 CALIFORNIA

1.77

 Califor

1.70

 Californian

1.62

 Calif

1.62

CALIFORNIA

1.59

 Californie

1.59

Los

1.52

 california

1.52

Activations Density 0.882%

structured legal or administrative content related to entities and documents

No Comments

No Known Activations