INDEX

Explanations

terms related to legal concepts and processes

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

OCCURRED

-0.54

createStatement

-0.50

BagLayout

-0.50

信

-0.50

 arada

-0.49

unut

-0.49

 imaginar

-0.49

layoutParams

-0.48

WithFormat

-0.48

multer

-0.48

POSITIVE LOGITS

Xna

0.79

 كومونز

0.62

 برانيه

0.61

expandindo

0.59

schrift

0.57

rostis

0.57

 المعيارى

0.57

romyalgia

0.56

ரிய

0.56

 Whig

0.56

Activations Density 1.445%

terms related to legal concepts and processes

No Comments

No Known Activations