INDEX

Explanations

code comments and license-related information

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

start of code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

AndEndTag

-1.05

 '\\;'

-1.02

OGND

-0.94

webElement

-0.81

sidemargin

-0.80

findpost

-0.75

 дописавши

-0.74

 للاسماء

-0.72

RectangleBorder

-0.71

twimg

-0.71

POSITIVE LOGITS

SEC

0.49

Ży

0.45

ooker

0.45

 Maat

0.42

 Ibidem

0.42

 vacuum

0.41

 Meda

0.41

HEAST

0.41

ざ

0.40

OnPage

0.40

Activations Density 0.009%

code comments and license-related information

start of code

No Comments

No Known Activations