INDEX

Explanations

questions related to measurements and conversions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

出版年

-0.55

ConstraintMaker

-0.53

bkz

-0.52

Javadoc

-0.52

ρίς

-0.50

MethodImpl

-0.48

lyl

-0.47

 arşivlendi

-0.46

âtre

-0.46

Literatuur

-0.45

POSITIVE LOGITS

RenderAtEndOf

0.74

{?}

0.59

aarrggbb

0.57

MessageTagHelper

0.56

RTCF

0.54

imals

0.54

PreExecute

0.54

Abitanti

0.53

 cistern

0.53

цездатний

0.53

Activations Density 2.904%

questions related to measurements and conversions

No Comments

No Known Activations