INDEX

Explanations

technical terms related to programming, data models, and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 global

-0.58

atecas

-0.56

min

-0.51

 media

-0.50

 Media

-0.49

 Global

-0.47

ologous

-0.47

no

-0.47

the

-0.47

flik

-0.47

POSITIVE LOGITS

 Majefty

1.02

 itſelf

0.96

 fubject

0.96

 Theſe

0.94

 theſe

0.91

 Cæsar

0.91

 feroit

0.89

 enfans

0.89

 Shakspeare

0.89

 themſelves

0.88

Activations Density 3.178%

technical terms related to programming, data models, and attributes

No Comments

No Known Activations