INDEX

Explanations

titles and related metadata in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

wnież

-0.63

 enfans

-0.62

 riuscito

-0.61

 costumi

-0.60

 círculo

-0.60

 éprou

-0.60

 mangiare

-0.60

Tämä

-0.59

 droog

-0.58

 reproach

-0.58

POSITIVE LOGITS

Title

1.27

 Title

1.02

title

0.90

 title

0.87

awtextra

0.74

 TITLE

0.72

fromnode

0.71

 titled

0.69

 titles

0.69

出版年

0.67

Activations Density 0.014%

titles and related metadata in documents

No Comments

No Known Activations