INDEX

Explanations

mathematical expressions or values in scientific notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

-0.41

 dép

-0.41

-0.40

ore

-0.40

fele

-0.40

署

-0.40

 kulit

-0.40

 bañ

-0.39

мор

-0.39

POSITIVE LOGITS

IntoConstraints

1.26

ंदीखरीदारी

1.06

providedIn

1.06

AddTagHelper

1.05

存于互联网档案馆

1.03

enderror

1.03

 MotionEvent

1.01

 MainAxisSize

0.98

 StatefulWidget

0.97

UnusedPrivate

0.97

Activations Density 0.181%

mathematical expressions or values in scientific notations

No Comments

No Known Activations