INDEX

Explanations

proper nouns, specifically names and significant dates or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

دانشنامهٔ

-0.63

 Normdatei

-0.56

hyrchwyd

-0.52

television

-0.51

 Lyndon

-0.50

 Reagan

-0.50

limard

-0.50

ApiException

-0.50

Referències

-0.50

 Kepler

-0.50

POSITIVE LOGITS

 Obrador

0.39

Tikang

0.39

StartTag

0.34

 railroad

0.34

manjaro

0.33

 podéis

0.33

 Railways

0.33

 railway

0.32

phosa

0.32

 correctamente

0.32

Activations Density 0.680%

proper nouns, specifically names and significant dates or events

No Comments

No Known Activations