INDEX

Explanations

patterns of high activity values that indicate significant elements in programming or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 FetchType

-0.94

 more

-0.84

more

-0.73

More

-0.65

 más

-0.65

 MORE

-0.64

 mais

-0.61

 более

-0.59

 كومونز

-0.58

 mehr

-0.58

POSITIVE LOGITS

 HttpNotFound

0.61

 viewType

0.61

prefixer

0.58

UnknownFields

0.53

 pageable

0.53

 kaarangay

0.51

0.49

RemoteException

0.49

ısında

0.49

Tembelea

0.48

Activations Density 0.031%

patterns of high activity values that indicate significant elements in programming or technical contexts

No Comments

No Known Activations