INDEX

Explanations

references to advice or suggestions for improvement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/

-0.86

"){

-0.81

 BrowserRouter

-0.79

'},

-0.78

SpringRunner

-0.78

UnknownFieldSet

-0.75

parsedMessage

-0.73

\{\\

-0.72

 }}$}

-0.70

,$_

-0.70

POSITIVE LOGITS

 tips

2.97

tip

2.96

Tip

2.83

 Tips

2.75

Tip

2.69

tips

2.57

Tips

2.55

tip

2.54

TIP

2.38

 TIPS

2.30

Activations Density 0.045%

references to advice or suggestions for improvement

No Comments

No Known Activations