INDEX

Explanations

technical terms related to programming and databases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 monos

-0.53

 reference

-0.47

 ricord

-0.47

 refere

-0.47

 remember

-0.47

 vigne

-0.47

 drinker

-0.47

toBeDefined

-0.45

resizable

-0.44

ElementException

-0.44

POSITIVE LOGITS

 estekak

0.78

 setuptools

0.76

didSet

0.71

 BorderRadius

0.70

Pel

0.70

Cy

0.67

 GenerationType

0.65

 Kinetic

0.65

woosh

0.63

ye

0.63

Activations Density 2.407%

technical terms related to programming and databases

No Comments

No Known Activations