INDEX

Explanations

specific keywords or phrases related to operational or mechanical processes

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

 مخطط

-0.53

Fun

-0.49

ULTS

-0.49

ERG

-0.49

 thinking

-0.47

grove

-0.44

ļi

-0.42

UT

-0.42

órc

-0.41

ļa

-0.41

POSITIVE LOGITS

complexContent

0.85

__':

0.80

__":

0.76

 дописавши

0.73

parsedMessage

0.71

 विश्वसनीयता

0.70

 виправивши

0.69

 BorderRadius

0.67

 ImportError

0.65

__).

0.62

Activations Density 0.524%

specific keywords or phrases related to operational or mechanical processes

No Comments

No Known Activations