INDEX

Explanations

verbs ending in 'in' and 'ing' with a bias for slang

oai_token-act-pair · gemini-2.0-flash

Foreign language/code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 examples

-1.37

 example

-1.30

 Examples

-1.18

example

-1.17

examples

-1.13

Examples

-1.13

Example

-1.09

 EXAMPLES

-1.03

 ejemplos

-1.03

 Example

-1.01

POSITIVE LOGITS

InjectAttribute

0.97

elemField

0.85

 Baillargeon

0.76

richTextPanel

0.74

ThroughAttribute

0.73

aarrggbb

0.73

contentLoaded

0.72

 通販

0.70

 дописавши

0.69

 Мексичка

0.68

Activations Density 0.303%

verbs ending in 'in' and 'ing' with a bias for slang

Foreign language/code

No Known Activations

verbs ending in 'in' and 'ing' with a bias for slang

Foreign language/code

No Known Activations