INDEX

Explanations

the word "significantly" and nearby words that indicate an increase or decrease

oai_token-act-pair · gemini-2.0-flash

significantly

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Datuak

-0.66

 denen

-0.55

ProgressHUD

-0.53

GEBURTS

-0.51

ISupport

-0.50

DeleteBehavior

-0.49

TagMode

-0.49

sweise

-0.48

<-

-0.47

enumi

-0.46

POSITIVE LOGITS

<bos>

1.41

 occaf

0.63

 reaſon

0.62

 neceff

0.61

IUrlHelper

0.60

CodedInputStream

0.60

 occafion

0.59

LEMMA

0.57

 itſelf

0.57

 Cæsar

0.57

Activations Density 1.001%

the word "significantly" and nearby words that indicate an increase or decrease

significantly

No Comments

No Known Activations