INDEX

Explanations

references to graphic and mathematical content in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

PARATOR

-0.59

>*/

-0.58

tvguidetime

-0.56

Pos

-0.56

abestanden

-0.56

ufel

-0.55

ReusableCell

-0.53

querySelectorAll

-0.53

ᅠ

-0.52

okin

-0.52

POSITIVE LOGITS

graphicx

2.79

InputBorder

0.67

bewerken

0.63

epsfig

0.61

 المعيارى

0.59

hyperref

0.59

amsmath

0.59

httphttps

0.57

 Zing

0.57

 Administrativna

0.56

Activations Density 0.030%

references to graphic and mathematical content in documents

No Comments

No Known Activations