INDEX

Explanations

mentions of sleep and related concepts

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

 Majors

-0.45

 Firmen

-0.45

Sni

-0.44

 amarela

-0.43

GrantedAuthority

-0.42

 Magnitude

-0.42

 taint

-0.41

 Bravo

-0.41

esterno

-0.41

 amarelo

-0.41

POSITIVE LOGITS

 SLEEP

1.05

Sleep

1.03

 sleep

1.02

 Sleep

1.02

sleep

1.01

SLEEP

0.98

 sleeping

0.89

Sleeping

0.89

 Sleeping

0.88

 sleeps

0.88

Activations Density 0.164%

mentions of sleep and related concepts

No Comments

No Known Activations