INDEX

Explanations

conjunctions and phrases indicating connections or relationships among various concepts

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

最快更新

-0.63

arja

-0.59

lishes

-0.56

рация

-0.56

})));

-0.56

Geografi

-0.55

kew

-0.53

 initWithFrame

-0.52

 proceeds

-0.51

 Peti

-0.51

POSITIVE LOGITS

RegressionTest

0.83

fjspx

0.65

édez

0.59

udessa

0.58

zyż

0.56

MLLoader

0.54

مراجع

0.54

 hogyan

0.54

 miasto

0.53

втра

0.53

Activations Density 0.354%

conjunctions and phrases indicating connections or relationships among various concepts

No Comments

No Known Activations