INDEX

Explanations

terms indicating uniqueness or significant characteristics

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

 itſelf

-0.57

 againſt

-0.53

ajemy

-0.51

 invloed

-0.49

 partiellement

-0.49

 ſeveral

-0.48

ğimiz

-0.48

Wall

-0.47

Useful

-0.47

Seine

-0.46

POSITIVE LOGITS

 فريبيس

0.77

styleable

0.68

fillType

0.61

aarrggbb

0.59

rungsseite

0.58

 unknownFields

0.58

 disambiguazione

0.55

permum

0.55

Beschreibung

0.55

rrggbb

0.54

Activations Density 0.501%

terms indicating uniqueness or significant characteristics

No Comments

No Known Activations