INDEX

Explanations

references to the term "pen" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enderror

-0.68

TypedDataSet

-0.60

Affirmed

-0.52

addContainerGap

-0.52

LookAnd

-0.50

Демографія

-0.49

 createContext

-0.49

bmod

-0.48

SystemColors

-0.46

ImageIO

-0.46

POSITIVE LOGITS

insular

0.60

ultimate

0.59

manship

0.56

umbra

0.54

setVerticalGroup

0.53

 Pals

0.53

 pusher

0.52

ciled

0.52

elope

0.52

 Normdatei

0.51

Activations Density 0.208%

references to the term "pen" and its variations

No Comments

No Known Activations