INDEX

Explanations

references to specific guidelines or frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AccessException

-0.33

 Ashraf

-0.33

 ComVisible

-0.33

CBA

-0.32

 spit

-0.32

TUS

-0.32

 hồi

-0.32

 Василь

-0.32

runApp

-0.31

canes

-0.31

POSITIVE LOGITS

SD

1.06

VD

1.03

Cd

1.02

RD

1.02

fd

1.02

MD

1.01

SD

1.01

FD

0.99

PD

0.99

sd

0.98

Activations Density 0.624%

references to specific guidelines or frameworks

No Comments

No Known Activations