INDEX

Explanations

numerical values and parameters in a context likely related to technical or legal documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

aarrggbb

-0.95

 كومونز

-0.71

 doInBackground

-0.69

titleMargin

-0.69

 متعلقه

-0.68

 שוליים

-0.65

 ویکی‌پدیا

-0.60

tagHelperRunner

-0.60

 ویکی‌پدیای

-0.60

AnchorStyles

-0.59

POSITIVE LOGITS

0.58

 CURIAM

0.55

()+"

0.54

клопе

0.51

 resourceCulture

0.50

обеди

0.49

 Valkyrie

0.48

 VIDEOTAPE

0.47

scalatest

0.46

Activations Density 0.222%

numerical values and parameters in a context likely related to technical or legal documents

No Comments

No Known Activations