INDEX

Explanations

that

np_max-act-logits · gemini-2.0-flash

sentences that use the word 'that' as a relative pronoun

oai_token-act-pair · gemini-2.0-flash

code or markup

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 européennes

-0.49

 públicas

-0.43

jén

-0.43

قای

-0.43

viewWillAppear

-0.42

блі

-0.42

Bronnen

-0.42

 réalisées

-0.41

cambi

-0.41

 elettron

-0.41

POSITIVE LOGITS

 betweenstory

0.97

titleMargin

0.92

 Мексичка

0.91

 otomatig

0.83

DockStyle

0.77

 مشين

0.71

WithIOException

0.71

IVEREF

0.71

expandindo

0.69

 MenuView

0.69

Activations Density 1.191%

that

sentences that use the word 'that' as a relative pronoun

code or markup

No Comments

No Known Activations