INDEX

Explanations

contexts and phrases that imply examples or clarifications

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

Follows "for" and means "example" or "instance"

np_acts-logits-general · gemini-2.0-flash

introduces examples or specific points

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

 gynnwys

-0.88

Personensuche

-0.87

 Wikimedijinoj

-0.86

OGND

-0.82

AnchorStyles

-0.76

 Meksiku

-0.76

InjectAttribute

-0.74

 pinulongan

-0.72

withIdentifier

-0.72

Diwedd

-0.70

POSITIVE LOGITS

دیگر

0.58

الدراسه

0.55

 asemenea

0.52

 benzina

0.47

vidia

0.47

Spoiler

0.47

Външни

0.47

Aiheesta

0.47

 nouve

0.47

ocarditis

0.46

Activations Density 1.041%

contexts and phrases that imply examples or clarifications

Follows "for" and means "example" or "instance"

introduces examples or specific points

No Comments

No Known Activations