INDEX

Explanations

sentences describing a character's weapons, abilities, and transformations.

oai_token-act-pair · gemini-2.0-flash

Kyuranger

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 hlavy

-0.50

UnifiedTopology

-0.44

 Tweede

-0.44

 thiệu

-0.43

 références

-0.43

Références

-0.43

ături

-0.42

ležité

-0.42

Gotcha

-0.41

 scatola

-0.41

POSITIVE LOGITS

AndEndTag

0.84

windowFixed

0.69

XmlAccessType

0.69

+#+#

0.62

dafx

0.60

 nonatomic

0.60

 positron

0.60

Xna

0.59

صدر

0.59

InjectAttribute

0.57

Activations Density 1.853%

sentences describing a character's weapons, abilities, and transformations.

Kyuranger

No Comments

No Known Activations