INDEX

Explanations

syntax constructs related to regular expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ویکی‌پدی

-0.56

estacks

-0.48

 lavable

-0.46

 endblock

-0.46

MIDDLEWARE

-0.46

 emperador

-0.43

 lenker

-0.43

 ciudadana

-0.42

 zijne

-0.42

IContainer

-0.42

POSITIVE LOGITS

(?:

0.71

OCS

0.51

iap

0.48

">(</

0.48

ToBe

0.46

 Slick

0.46

 Rafa

0.45

 Warne

0.45

 Fian

0.45

@(

0.45

Activations Density 0.005%

syntax constructs related to regular expressions

No Comments

No Known Activations