INDEX

Explanations

causal phrases and discussions around decisions and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 todėl

-0.47

 inoltre

-0.44

Mo

-0.44

alten

-0.41

 Polo

-0.40

Ho

-0.40

Mol

-0.40

which

-0.40

novel

-0.40

Mol

-0.40

POSITIVE LOGITS

 InputDecoration

1.07

 >=",

0.87

 تانيه

0.85

 المعيارى

0.82

 Ведь

0.77

 przecież

0.77

SOUNDBITE

0.72

 TÉCNICA

0.72

invokeLater

0.71

Ведь

0.71

Activations Density 0.263%

causal phrases and discussions around decisions and their implications

No Comments

No Known Activations