INDEX

Explanations

words related to research and experimentation

oai_token-act-pair · gemini-2.0-flash

test

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

<bos>

-0.59

CppMethod

-0.57

Chham

-0.57

GEBURTS

-0.52

DotNetBar

-0.48

-0.47

arev

-0.47

rem

-0.47

asantry

-0.45

olith

-0.45

POSITIVE LOGITS

 theſe

0.79

 ſeveral

0.78

 purpoſe

0.75

 fince

0.73

 fevere

0.73

 Monfieur

0.72

 leaſt

0.72

 يتيمه

0.72

 uſe

0.72

 quæ

0.71

Activations Density 0.748%

words related to research and experimentation

test

No Comments

No Known Activations