INDEX

Explanations

references to enjoyment and fun activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Quo

-0.50

 cejas

-0.48

 monasterio

-0.46

 polaire

-0.45

 Ellos

-0.44

zeile

-0.44

 Normdatei

-0.44

 Monats

-0.42

лтемелер

-0.42

 aquilo

-0.41

POSITIVE LOGITS

fun

1.02

Fun

0.98

fun

0.98

FUN

0.96

Fun

0.94

FUN

0.91

 divertimento

0.87

 diversión

0.81

 Spaß

0.75

 divertir

0.70

Activations Density 0.120%

references to enjoyment and fun activities

No Comments

No Known Activations