INDEX

Explanations

beginnings of new sections or paragraphs in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Responsable

-0.53

 Nymp

-0.48

 Sponge

-0.47

lient

-0.45

 Nobel

-0.44

lton

-0.43

 flore

-0.43

 keyboards

-0.43

èvent

-0.42

 tule

-0.42

POSITIVE LOGITS

Datuak

0.84

XmlAccessType

0.81

oredCriteria

0.78

 CreateTagHelper

0.78

tagHelperRunner

0.75

protoimpl

0.73

OGND

0.73

 صوتيه

0.73

GOTREF

0.71

IntoConstraints

0.64

Activations Density 0.246%

beginnings of new sections or paragraphs in a text

No Comments

No Known Activations