INDEX

Explanations

references to specific outcomes or evaluations 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 @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

BeginInit

-0.57

 المعيارى

-0.54

upyter

-0.53

க்கு

-0.53

 natale

-0.52

FieldBuilder

-0.50

ebaran

-0.49

rages

-0.48

ristor

-0.48

IsTrue

-0.48

POSITIVE LOGITS

 autorytatywna

0.81

<bos>

0.72

 disambiguazione

0.60

IUrlHelper

0.60

 ostavi

0.59

 betweenstory

0.56

Erstellt

0.55

 oprot

0.55

 Biôgrafia

0.54

ItemBackground

0.53

Activations Density 0.243%

references to specific outcomes or evaluations in various contexts

No Comments

No Known Activations