INDEX

Explanations

a pattern of alphanumeric characters and their associated values in a structured dataset

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

ValueStyle

-0.78

__":

-0.75

tanleria

-0.65

oa̍t

-0.65

__":

-0.64

 >=",

-0.63

########.

-0.63

AntiForgeryToken

-0.62

providedIn

-0.61

 surla

-0.60

POSITIVE LOGITS

colo

0.60

aronder

0.56

olingo

0.51

charCodeAt

0.51

 userManager

0.49

 falling

0.49

ypsies

0.49

stackrel

0.49

âm

0.48

 Svensson

0.47

Activations Density 1.316%

a pattern of alphanumeric characters and their associated values in a structured dataset

No Comments

No Known Activations