INDEX

Explanations

classes and methods in programming code

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

CUDA device properties or capabilities

np_acts-logits-general · gemini-2.0-flash

device information and capabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-0.70

-0.55

on

-0.54

-0.53

-0.51

in

-0.49

íncia

-0.47

co

-0.46

and

-0.46

POSITIVE LOGITS

 ſind

1.03

 Anſ

1.02

 ་་

0.99

Datuak

0.98

Efq

0.94

 يتيمه

0.93

بوابة

0.89

 Conſ

0.87

 referrerpolicy

0.86

 photolibrary

0.86

Activations Density 1.176%

classes and methods in programming code

CUDA device properties or capabilities

device information and capabilities

No Comments

No Known Activations