INDEX

Explanations

phrases related to effort and willingness to help

oai_token-act-pair · gemini-2.0-flash

effort/ability

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

webElement

-0.63

AxisAlignment

-0.62

 Agamemnon

-0.60

iaomi

-0.55

 consultato

-0.54

 Hopf

-0.54

 auroit

-0.53

 LoginForm

-0.53

atare

-0.53

 étoit

-0.52

POSITIVE LOGITS

to

0.65

whole

0.54

abestanden

0.51

yet

0.47

TagHelper

0.46

 OMIT

0.46

AddHtmlAttribute

0.46

fetchone

0.46

intera

0.45

WORTH

0.45

Activations Density 5.689%

phrases related to effort and willingness to help

effort/ability

No Comments

No Known Activations