INDEX

Explanations

mentions of something being found, created or revealed.

oai_token-act-pair · gemini-2.0-flash

discovery

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 discover

-1.91

 discovery

-1.88

 discovered

-1.77

 discovering

-1.76

discover

-1.74

Discover

-1.72

 discovers

-1.71

 Discover

-1.70

 Discovery

-1.64

Discovery

-1.64

POSITIVE LOGITS

ReusableCell

0.77

 Excuse

0.57

IntoConstraints

0.56

eseorang

0.54

adaptiveStyles

0.53

MLLoader

0.52

 Luch

0.52

iliary

0.52

 muualla

0.52

 Epif

0.51

Activations Density 8.940%

mentions of something being found, created or revealed.

discovery

No Comments

No Known Activations