INDEX

Explanations

phrases related to collecting or listing terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

IVEREF

-0.70

RUnlock

-0.64

InvalidProtocol

-0.62

GOTREF

-0.60

WritableDatabase

-0.59

AddTagHelper

-0.57

AsStream

-0.56

atschappij

-0.54

DeleteBehavior

-0.54

 بتاريخ

-0.53

POSITIVE LOGITS

:✨

1.00

 autorytatywna

0.56

rungsseite

0.54

httphttps

0.52

 endforeach

0.52

########.

0.51

\{\\

0.49

()?.

0.48

initView

0.48

botten

0.47

Activations Density 0.014%

phrases related to collecting or listing terms

No Comments

No Known Activations