INDEX

Explanations

instances of the word "define" and its variations, indicating a focus on definitions and explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

KommentareTeilen

-0.71

ฤษ

-0.68

WriteTo

-0.57

سباب

-0.56

Brun

-0.55

 Beren

-0.54

▻

-0.53

IContainer

-0.53

capital

-0.53

kadot

-0.52

POSITIVE LOGITS

 defines

1.16

 Defined

1.15

 define

1.14

 Defines

1.13

 defined

1.10

 DEFINITION

1.10

 Define

1.09

Defines

1.09

defines

1.08

 Defin

1.07

Activations Density 0.187%

instances of the word "define" and its variations, indicating a focus on definitions and explanations

No Comments

No Known Activations