INDEX

Explanations

terms related to changes and counts in data systems, especially in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Predecesor

-0.51

afficheront

-0.49

TableBody

-0.48

 goodbye

-0.47

Cre

-0.44

 Rodrig

-0.44

렀

-0.42

حياتها

-0.42

RTE

-0.41

uity

-0.41

POSITIVE LOGITS

findpost

0.58

帖最后由

0.57

 BigNumberish

0.56

 désol

0.56

RenderAtEndOf

0.56

 périph

0.56

AndEndTag

0.56

 ProtoMessage

0.56

 flesta

0.55

 circonstances

0.55

Activations Density 0.638%

terms related to changes and counts in data systems, especially in scientific contexts

No Comments

No Known Activations