INDEX

Explanations

mathematical symbols and notation used in explanations or analyses

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

Negative Logits

Gambas

-0.62

 متعلقه

-0.53

Билгалдахарш

-0.51

>{@

-0.50

Weh

-0.50

FieldError

-0.49

compañ

-0.45

 mør

-0.45

 podjela

-0.45

 steder

-0.44

POSITIVE LOGITS

|}{$

0.89

|}{

0.86

AnchorStyles

0.71

 ModelRenderer

0.71

runApp

0.71

DrawerLayout

0.68

FormTagHelper

0.65

 onPostExecute

0.65

 surla

0.64

+:+

0.63

Activations Density 0.187%

mathematical symbols and notation used in explanations or analyses

No Known Activations