INDEX

Explanations

words related to the names of characters and teams from a specific television show

oai_token-act-pair · gemini-2.0-flash

ami

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Administrativna

-0.72

IntoConstraints

-0.69

DockStyle

-0.69

 Majefty

-0.66

 RIPRODUZIONE

-0.66

=$?

-0.66

//

-0.66

Personendaten

-0.65

Efq

-0.65

 itſelf

-0.63

POSITIVE LOGITS

SPATH

0.62

Insee

0.58

<bos>

0.55

PhysRevD

0.55

 reticulum

0.51

Delta

0.48

Morfo

0.47

튀

0.47

oxane

0.47

 bruto

0.46

Activations Density 7.392%

words related to the names of characters and teams from a specific television show

ami

No Comments

No Known Activations