INDEX

Explanations

references to usage and implementation of various features or parameters in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

MigrationBuilder

-0.48

AddTagHelper

-0.44

pulseira

-0.42

 متعلقه

-0.42

WithIOException

-0.41

 Italijani

-0.40

protoimpl

-0.40

GOTREF

-0.39

 vaikka

-0.38

 menak

-0.38

POSITIVE LOGITS

 để

0.73

 כדי

0.66

 чтобы

0.64

 щоб

0.62

เพื่อ

0.53

 чтоб

0.52

Чтобы

0.51

 upang

0.51

 inorder

0.49

aby

0.45

Activations Density 0.976%

references to usage and implementation of various features or parameters in a technical context

No Comments

No Known Activations