INDEX

Explanations

words related to the usage and application of items or methods 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 AssemblyCulture

-0.71

XmlAccessType

-0.70

+#+#

-0.66

RenderAtEndOf

-0.66

 defaultstate

-0.61

GEBURTSDATUM

-0.61

BeginContext

-0.60

OrNil

-0.58

AndEndTag

-0.58

SafeMath

-0.57

POSITIVE LOGITS

 Used

0.72

 Verwendung

0.71

 gebruik

0.63

makaian

0.62

 χρήση

0.61

Used

0.61

Use

0.58

 utilisez

0.58

 used

0.58

 expériment

0.58

Activations Density 0.339%

words related to the usage and application of items or methods in various contexts

No Comments

No Known Activations