INDEX

Explanations

mentions of entities starting with the letter "L"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 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

XmlAccessType

-0.78

 nonatomic

-0.62

jsxFileName

-0.61

ISupport

-0.61

MockBean

-0.60

EDEFAULT

-0.58

 esboço

-0.57

AddTagHelper

-0.57

각주

-0.57

aarrggbb

-0.56

POSITIVE LOGITS

0.47

 distanciation

0.46

homonymie

0.45

0.43

Diweddarwch

0.41

insee

0.41

 actualité

0.40

ArgsConstructor

0.40

erna

0.40

Launching

0.39

Activations Density 0.231%

mentions of entities starting with the letter "L"

No Comments

No Known Activations