INDEX

Explanations

patterns of numerical or alphanumeric sequences indicating data IDs or codes

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

Characters after hexadecimal numbers

np_acts-logits-general · gemini-2.0-flash

hexadecimal characters and numbers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

SourceChecksum

-0.94

WebVitals

-0.87

#+#

-0.81

MigrationBuilder

-0.79

 дописавши

-0.78

 BoxDecoration

-0.75

İstinadlar

-0.74

MemoryWarning

-0.74

NameInMap

-0.73

UIControlState

-0.72

POSITIVE LOGITS

 énergé

0.44

 sélectionnés

0.42

ेशा

0.41

 apó

0.41

 alone

0.37

 fermés

0.37

ED

0.36

 ketiga

0.36

žad

0.36

/</

0.35

Activations Density 0.301%

patterns of numerical or alphanumeric sequences indicating data IDs or codes

Characters after hexadecimal numbers

hexadecimal characters and numbers

No Comments

No Known Activations