INDEX

Explanations

mathematical expressions and symbols related to sequences or sets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

หลัง

-0.43

↵↵

-0.42

“

-0.42

 assass

-0.41

сми

-0.40

-0.39

 esboço

-0.39

ensch

-0.39

eaf

-0.39

gı

-0.38

POSITIVE LOGITS

GOTREF

0.84

 تضيفلها

0.74

 InputDecoration

0.69

 Roskov

0.69

ronpa

0.68

iNdEx

0.68

Демографія

0.68

basicConfig

0.68

:+:

0.67

GraphicsUnit

0.67

Activations Density 1.093%

mathematical expressions and symbols related to sequences or sets

No Comments

No Known Activations