INDEX

Explanations

versions of software or components in a list format

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

Follows a period

np_acts-logits-general · gemini-2.0-flash

software versions and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 متعلقه

-0.95

 بيها

-0.92

脚注の使い方

-0.86

 المعيارى

-0.85

ConstraintMaker

-0.84

 يتيمه

-0.83

MLLoader

-0.79

RegistryLite

-0.76

 صوتيه

-0.75

VIAF

-0.75

POSITIVE LOGITS

 Personally

0.44

ובן

0.42

initas

0.41

 Bergmann

0.41

批

0.40

hout

0.40

melte

0.40

 अलावा

0.40

انه

0.40

 fundamentales

0.39

Activations Density 0.163%

versions of software or components in a list format

Follows a period

software versions and names

No Comments

No Known Activations