INDEX

Explanations

references to tables and configurations in various code snippets

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

 lieb

-0.51

maat

-0.48

]")]

-0.48

complexContent

-0.47

новниш

-0.45

medriver

-0.45

 columnIndex

-0.44

jou

-0.44

 numerus

-0.43

Secondly

-0.42

POSITIVE LOGITS

 schematic

0.78

 screenshot

0.75

示意图

0.70

 diagram

0.69

 screenshots

0.69

 Diagram

0.66

 arată

0.64

 flowchart

0.64

 results

0.64

 overview

0.63

Activations Density 0.627%

references to tables and configurations in various code snippets

No Comments

No Known Activations