INDEX

Explanations

mathematical symbols and notations

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

<start_of_turn> user

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

IntoConstraints

-0.97

 ProtoMessage

-0.97

AddTagHelper

-0.94

Tikang

-0.91

 Италијани

-0.87

 kasarigan

-0.85

reportWebVitals

-0.76

bootstrapcdn

-0.76

 kaarangay

-0.75

 OFDb

-0.75

POSITIVE LOGITS

Vos

0.27

 building

0.27

LayoutPanel

0.26

inter

0.25

曾

0.25

Had

0.24

 gedung

0.23

 zaji

0.23

Building

0.23

AddRange

0.22

Activations Density 0.000%

mathematical symbols and notations

<start_of_turn> user

No Comments

No Known Activations