INDEX

Explanations

content related to figures or visual representations in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 ponte

-0.48

 bote

-0.47

Method

-0.44

ThroughAttribute

-0.44

addColumn

-0.43

juvant

-0.43

quila

-0.42

┌

-0.42

source

-0.42

 heter

-0.41

POSITIVE LOGITS

figsize

0.91

verwijspagina

0.89

 figs

0.86

 figures

0.86

 Figures

0.84

 FIGURES

0.82

 LoggerFactory

0.81

jsxFileName

0.80

 nahilalakip

0.78

Figures

0.78

Activations Density 0.349%

content related to figures or visual representations in a scientific context

No Comments

No Known Activations