INDEX

Explanations

phrases related to leaving or transitioning from one state or place to another

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 continúas

-0.79

DrawerToggle

-0.69

出版年

-0.65

#+#

-0.64

}{*}{}

-0.60

BufferException

-0.59

 glab

-0.58

cranial

-0.58

 NgModule

-0.57

avía

-0.56

POSITIVE LOGITS

Erreferentziak

0.50

 beginnetje

0.49

protoimpl

0.49

zul

0.49

elab

0.48

Glej

0.45

XmlAccessType

0.44

WarningLevel

0.43

meri

0.42

quy

0.42

Activations Density 0.212%

phrases related to leaving or transitioning from one state or place to another

No Comments

No Known Activations