INDEX

Explanations

numerical information and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

tvguidetime

-0.78

MENAFN

-0.76

AndEndTag

-0.72

contentLoaded

-0.67

Hauptartikel

-0.65

 שוליים

-0.64

iecie

-0.63

rungsseite

-0.62

encodeWith

-0.61

 محفوظة

-0.59

POSITIVE LOGITS

EndGlobalSection

0.67

Хьажоргаш

0.55

unknownFields

0.54

 Flanders

0.48

 esportivo

0.47

 Moslem

0.47

 Fase

0.46

 insensible

0.45

 chłop

0.45

biker

0.44

Activations Density 0.422%

numerical information and statistics

No Comments

No Known Activations