INDEX

Explanations

mentions of the term "Bel."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 preuve

-0.73

 calore

-0.65

 sottile

-0.64

 élector

-0.63

 sauvages

-0.62

 segno

-0.61

 épis

-0.61

 montagna

-0.61

 fotográfico

-0.60

 normaux

-0.60

POSITIVE LOGITS

Bel

1.29

Bel

1.17

BEL

1.16

bel

1.15

bel

1.04

BEL

0.99

 Belg

0.72

 betweenstory

0.71

bels

0.65

irical

0.64

Activations Density 0.079%

mentions of the term "Bel."

No Comments

No Known Activations