INDEX

Explanations

concepts related to cognitive function and mental processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ContentAsync

-0.58

Essentials

-0.51

estimm

-0.48

 sessile

-0.48

 anonyme

-0.47

amatkan

-0.47

Mention

-0.45

 logistic

-0.45

Pron

-0.45

 ajustado

-0.44

POSITIVE LOGITS

 brain

1.46

 minds

1.37

 brains

1.30

 mind

1.24

brain

1.18

 Brain

1.14

 cognitive

1.14

Brain

1.14

 MIND

1.11

 BRAIN

1.09

Activations Density 0.326%

concepts related to cognitive function and mental processes

No Comments

No Known Activations