INDEX

Explanations

punctuation marks or symbols typically used in writing

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

 estimés

-0.82

 يتيمه

-0.77

Tikang

-0.74

ⓧ

-0.73

 Barbier

-0.69

 Exteriores

-0.67

 Garanti

-0.67

ništvo

-0.66

ients

-0.65

POSITIVE LOGITS

]='\

0.78

rijfs

0.71

ientí

0.67

ۜ

0.65

ẓ

0.65

 väli

0.63

Yee

0.62

ésult

0.62

 éché

0.60

arange

0.59

Activations Density 0.098%

punctuation marks or symbols typically used in writing

No Comments

No Known Activations