INDEX

Explanations

mentions of sleep and waking behaviors or conditions

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

schaft

-0.49

 Forever

-0.47

 ISNI

-0.45

 depleted

-0.45

úncia

-0.44

lnie

-0.43

ngx

-0.43

hel

-0.43

 cél

-0.41

 bạc

-0.41

POSITIVE LOGITS

 awake

1.17

 waking

1.17

 wake

1.15

 woken

1.10

 wakes

1.07

 woke

1.06

 awakening

1.04

 awaken

1.04

wake

1.03

Wake

1.01

Activations Density 0.199%

mentions of sleep and waking behaviors or conditions

No Comments

No Known Activations