INDEX

Explanations

phrases where one thing is doing something to benefit another thing

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

icor

-0.49

builders

-0.45

 Potential

-0.45

டம்

-0.44

pD

-0.43

 financières

-0.43

caps

-0.42

pong

-0.42

uci

-0.42

 Apartment

-0.41

POSITIVE LOGITS

ValueStyle

0.78

tonode

0.76

 BoxFit

0.71

 المعيارى

0.70

detectChanges

0.70

ReusableCell

0.67

/\.

0.64

*/].

0.63

>*/

0.63

 كمان

0.63

Activations Density 0.737%

phrases where one thing is doing something to benefit another thing

No Comments

No Known Activations