INDEX

Explanations

code snippets dealing with boxes (often as a data structure)

oai_token-act-pair · gemini-2.0-flash

box

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

box

-2.89

Box

-2.72

box

-2.67

Box

-2.56

 boxes

-2.55

 Boxes

-2.44

BOX

-2.44

BOX

-2.42

boxes

-2.39

Boxes

-2.22

POSITIVE LOGITS

 onAnimation

0.54

WritableDatabase

0.48

dataProvider

0.44

padek

0.44

 braccio

0.43

hã

0.43

fib

0.42

 tumors

0.41

 nakalista

0.41

ettbewer

0.41

Activations Density 1.848%

code snippets dealing with boxes (often as a data structure)

box

No Comments

No Known Activations