INDEX

Explanations

formatting symbols and documentation related to code attributes or properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 kasarigan

-1.00

ConstraintMaker

-0.79

featureID

-0.78

 архивлан

-0.77

StoreMessageInfo

-0.74

ChildScrollView

-0.74

HasForeignKey

-0.74

 مواليد

-0.73

EFIAPI

-0.73

glTranslatef

-0.71

POSITIVE LOGITS

hid

0.49

hidden

0.49

 Hidden

0.48

 реа

0.46

 pard

0.46

hom

0.45

current

0.45

HET

0.45

getCurrent

0.44

crt

0.44

Activations Density 0.005%

formatting symbols and documentation related to code attributes or properties

No Comments

No Known Activations

formatting symbols and documentation related to code attributes or properties

No Comments

No Known Activations