INDEX

Explanations

negations, especially "not."

oai_token-act-pair · gemini-2.0-flash

negation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

出版年

-0.96

 فريبيس

-0.85

MigrationBuilder

-0.81

ftagPool

-0.78

antMatchers

-0.78

 समीक्षक

-0.77

 NSCoder

-0.76

ValueStyle

-0.74

Geplaatst

-0.72

GEBURTSDATUM

-0.72

POSITIVE LOGITS

an

0.61

the

0.45

 hyperbolic

0.44

 helping

0.44

<bos>

0.44

 something

0.41

 mencu

0.41

 working

0.40

Activations Density 0.192%

negations, especially "not."

negation

No Comments

No Known Activations