INDEX

Explanations

information related to specific locations and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

DockStyle

-0.67

 يتيمه

-0.59

 rubrique

-0.59

에도

-0.58

 referenties

-0.57

씩

-0.57

GraphicsUnit

-0.57

%");

-0.57

 déliv

-0.56

სქოლიო

-0.56

POSITIVE LOGITS

enumi

0.57

Tarih

0.48

 AspNetCore

0.48

 Réponses

0.47

CPtr

0.47

 afford

0.47

didSet

0.47

Ҭ

0.46

 لئے

0.45

Diwedd

0.45

Activations Density 1.364%

information related to specific locations and measurements

No Comments

No Known Activations