INDEX

Explanations

references to academic publications and institutions

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

 arşivlendi

-0.56

 Maori

-0.54

 Tasmanian

-0.54

 Etrus

-0.52

 ejerc

-0.52

ächs

-0.51

 Mersey

-0.49

 Indus

-0.48

 Fife

-0.48

 Urugu

-0.48

POSITIVE LOGITS

parsedMessage

0.77

хьтан

0.73

antMatchers

0.73

 ExecuteAsync

0.72

Chham

0.70



0.70

SharedDtor

0.66

NameInMap

0.65

RefNanny

0.64

 CURIAM

0.62

Activations Density 0.340%

references to academic publications and institutions

No Comments

No Known Activations