INDEX

Explanations

references to software packages, libraries, or APIs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 uſed

-0.65

 pleaſure

-0.63

 Monfieur

-0.61

Efq

-0.60

 căr

-0.60

uſ

-0.58

 ſeveral

-0.57

 Anſ

-0.57

 chofe

-0.56

 bună

-0.56

POSITIVE LOGITS

Geplaatst

0.86

 autorytatywna

0.85

RectangleBorder

0.83

ValueStyle

0.78

 pinulongan

0.76

 typelib

0.75

 beginnetje

0.73

 kaarangay

0.71

DataAnnotations

0.69

verwijspagina

0.68

Activations Density 0.012%

references to software packages, libraries, or APIs

No Comments

No Known Activations