INDEX

Explanations

numerical data within the text

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

ⓧ

-0.66

hoeddwyd

-0.63

 propOrder

-0.56

出版年

-0.56

AppMethodBeat

-0.56

tableFuture

-0.55

AutoField

-0.54

:+:

-0.54

SourceChecksum

-0.53

 دریافت‌شده

-0.52

POSITIVE LOGITS

 begge

0.58

BRUARY

0.57

ultuous

0.57

 tänka

0.57

$_"

0.57

 itſelf

0.56

AddTagHelper

0.55

("/:

0.53

medriver

0.53

blauch

0.53

Activations Density 0.428%

numerical data within the text

No Comments

No Known Activations