INDEX

Explanations

references to identical or matching elements across different contexts

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

HtmlAttribute

-0.62

 poaching

-0.60

AccessorTable

-0.59

setupUi

-0.58

yntaxException

-0.57

 "'";

-0.56

!("{

-0.56

bės

-0.56

 contextLoads

-0.55

 Dever

-0.54

POSITIVE LOGITS

same

0.83

 same

0.81

Same

0.78

 Same

0.65

 SAME

0.63

เดียว

0.63

twimg

0.61

 samma

0.60

 mêmes

0.58

 samme

0.58

Activations Density 0.407%

references to identical or matching elements across different contexts

No Comments

No Known Activations