INDEX

Explanations

documentation style comments typically used in programming or API documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ening

-0.52

-0.50

壮

-0.48

роди

-0.48

-0.47

TRANS

-0.47

load

-0.46

POSITIVE LOGITS

*/

2.51

*/

2.01

)*/

1.56

*/)

1.54

*/;

1.53

*/

1.51

.*/

1.43

})*/

1.43

*/,

1.42

>*/

1.38

Activations Density 0.078%

documentation style comments typically used in programming or API documentation

No Comments

No Known Activations