INDEX

Explanations

numbers and their formatted references in a legal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

RegressionTest

-0.46

Obrázky

-0.42

omycin

-0.41

ActionCreators

-0.40

ModelAdmin

-0.39

wage

-0.39

힣

-0.38

moy

-0.38

webs

-0.38

fights

-0.38

POSITIVE LOGITS

SharedCtor

0.54

енча

0.44

ReusableCell

0.44

ChildIndex

0.44

 onPostExecute

0.43

drawSprites

0.43

enumii

0.41

twimg

0.40

тельству

0.40

GEBURTSDATUM

0.40

Activations Density 0.059%

numbers and their formatted references in a legal context

No Comments

No Known Activations