INDEX

Explanations

patterns represented by numeric sequences or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 дописавши

-0.96

aarrggbb

-0.89

contentLoaded

-0.86

 AspNetCore

-0.83

InvalidProtocol

-0.82

 EconPapers

-0.81

 bezeichneter

-0.80

 AssemblyCulture

-0.80

 Wikimedijinoj

-0.80

 المعيارى

-0.80

POSITIVE LOGITS

↵

0.60

</h5>

0.57

CrossRef

0.54

Me

0.52

</strong>

0.52

Me

0.50

</em>

0.50

CEO

0.48

*/

0.48

</h3>

0.47

Activations Density 0.065%

patterns represented by numeric sequences or identifiers

No Comments

No Known Activations