INDEX

Explanations

block comments in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 AssemblyCulture

-0.91

 betweenstory

-0.87

)";

-0.71

iastes

-0.67

kkelen

-0.67

.";

-0.66

 Licence

-0.66

 licence

-0.66

*/

-0.65

äjä

-0.65

POSITIVE LOGITS

//

0.68

pushFollow

0.59

Cyfeiriadau

0.58

/*---

0.54

statt

0.53

retty

0.53

 Blau

0.51

AndPassword

0.51

jfree

0.49

 soins

0.48

Activations Density 0.085%

block comments in code

No Comments

No Known Activations