INDEX

Explanations

tokenized character sequences and their variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 miniaturka

-0.53

 sukienka

-0.49

 tričko

-0.49

Ehrungen

-0.48

 kwiaty

-0.46

 distinción

-0.46

 boneka

-0.46

 kolye

-0.46

 normaux

-0.46

 perbedaan

-0.45

POSITIVE LOGITS

IUrlHelper

0.59

WebElementEntity

0.57

Portail

0.57

 Taktlose

0.57

تقاوى

0.57

hyrchwyd

0.54

tvguidetime

0.52

 kasarigan

0.52

0.50

+#+

0.49

Activations Density 1.635%

tokenized character sequences and their variations

No Comments

No Known Activations