INDEX

Explanations

references to fundamental concepts or basic knowledge in various contexts

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

 Walkover

-0.86

eiro

-0.80

StringWriter

-0.75

 AssemblyTitle

-0.74

versite

-0.72

enegger

-0.71

kuuta

-0.71

 NSCoder

-0.71

ochrom

-0.71

 ferons

-0.71

POSITIVE LOGITS

 Basic

1.36

 Basics

1.33

 BASIC

1.32

Basic

1.26

basic

1.24

BASIC

1.24

 basic

1.23

 basics

1.22

Basics

1.21

basics

1.20

Activations Density 0.049%

references to fundamental concepts or basic knowledge in various contexts

No Comments

No Known Activations