INDEX

Explanations

the word "mantis" or names like Stacy Schwenk

oai_token-act-pair · 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

 autorytatywna

-0.81

 resourceCulture

-0.81

 Paglinawan

-0.79

 estimés

-0.78

verwijspagina

-0.77

 lenker

-0.75

tvguidetime

-0.73

SequentialGroup

-0.73

 CreateTagHelper

-0.73

 AssemblyCulture

-0.72

POSITIVE LOGITS

Efq

0.50

 himſelf

0.49

[toxicity=0]

0.47

Eſ

0.41

僕も

0.40

 whoſe

0.40

 downwards

0.40

Опис

0.40

 oneself

0.40

 tranſ

0.39

Activations Density 5.384%

the word "mantis" or names like Stacy Schwenk

No Comments

No Known Activations