INDEX

Explanations

details about physical spaces and their layouts

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

Follows numbers, or is a capitalized word

np_acts-logits-general · gemini-2.0-flash

numbers, math, and units

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

ReusableCell

-0.87

 Bioaccumulative

-0.63

unteers

-0.60

 مرئيه

-0.59

 الاطلاع

-0.58

 فريبيس

-0.57

mappedBy

-0.56

Lleg

-0.54

 înd

-0.53

 Audiodateien

-0.51

POSITIVE LOGITS

 Fully

0.62

 ProtoMessage

0.57

Covered

0.57

 fully

0.56

Fully

0.55

EndProject

0.54

enschappelijke

0.53

 Projektu

0.52

 covered

0.52

 armored

0.52

Activations Density 0.039%

details about physical spaces and their layouts

Follows numbers, or is a capitalized word

numbers, math, and units

No Comments

No Known Activations