INDEX

Explanations

words and phrases that describe a protagonist or character taking actions from the surrounding environment while possibly deep in thought.

oai_token-act-pair · gemini-2.0-flash

Narrations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

SourceChecksum

-1.05

 noDo

-0.84

 hini

-0.65

ագրություններ

-0.65

Vidite

-0.65

 Мексичка

-0.63

AddField

-0.60

memoized

-0.59

 ExecuteAsync

-0.59

msgTypes

-0.59

POSITIVE LOGITS

 virš

0.47

poda

0.47

Források

0.46

 vulga

0.44

Zgod

0.44

gridy

0.43

 trouvera

0.43

ėk

0.42

 sayap

0.42

 bulat

0.42

Activations Density 1.228%

words and phrases that describe a protagonist or character taking actions from the surrounding environment while possibly deep in thought.

Narrations

No Comments

No Known Activations

words and phrases that describe a protagonist or character taking actions from the surrounding environment while possibly deep in thought.

Narrations

No Comments

No Known Activations