INDEX

Explanations

specific relationships or associations between concepts or variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ifrance

-0.45

SARA

-0.43

वार

-0.42

 betweenstory

-0.41

디어

-0.39

-0.38

Dom

-0.37

erva

-0.37

random

-0.37

 sexuelle

-0.37

POSITIVE LOGITS

Datuak

0.89

NameInMap

0.81

CppCodeGen

0.72

WithIOException

0.72

 OFDb

0.69

則

0.68

AsUp

0.68

 Roskov

0.68

 мәкал

0.67

Referències

0.65

Activations Density 0.746%

specific relationships or associations between concepts or variables

No Comments

No Known Activations