INDEX

Explanations

proper nouns and specific entities, particularly names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

rinth

-0.72

følgelig

-0.72

 Brito

-0.72

】

-0.67

 ulei

-0.66

abancı

-0.65

 Adamson

-0.65

fuls

-0.64

 ordini

-0.63

繹

-0.63

POSITIVE LOGITS

 Euch

0.74

 poker

0.71

 AllAfrica

0.70

 Daley

0.68

 Holden

0.68

isPresent

0.68

 Dien

0.67

 présent

0.67

enegger

0.66

Dairy

0.66

Activations Density 2.051%

proper nouns and specific entities, particularly names and locations

No Comments

No Known Activations