INDEX

Explanations

descriptions of situations involving doors

oai_token-act-pair · gemini-2.0-flash

Mentions doors

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

 open

-1.94

open

-1.69

 opened

-1.66

Open

-1.62

 Open

-1.61

 opens

-1.59

 OPEN

-1.55

 Opened

-1.48

OPEN

-1.47

 Opens

-1.47

POSITIVE LOGITS

Personensuche

0.75

textAppearance

0.58

 <<<<<<<<<<<<<<

0.58

󠁣

0.57

InstanceState

0.56

Hentet

0.56

actionMode

0.56

 архивлан

0.55

**/

0.54

Hauptartikel

0.53

Activations Density 0.768%

descriptions of situations involving doors

Mentions doors

No Comments

No Known Activations