INDEX

Explanations

specific proper nouns related to individuals or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

findpost

-0.96

GEBURTSDATUM

-0.86

 nahilalakip

-0.81

WithIOException

-0.79

RTGC

-0.78

 utafitiHapana

-0.76

 CreateTagHelper

-0.75

 disambiguazione

-0.75

AlterField

-0.73

EndGlobalSection

-0.73

POSITIVE LOGITS

0.48

↵↵

0.41

 bane

0.40

astéroïdes

0.40

 giản

0.40

 Wiktionnaire

0.39

 Hill

0.39

اشتم

0.38

ché

0.38

</td>

0.38

Activations Density 0.235%

specific proper nouns related to individuals or characters

No Comments

No Known Activations