INDEX

Explanations

terminology related to cognitive processes and attention

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

BufferException

-0.43

 rheumatism

-0.42

ритори

-0.40

Demografie

-0.39

rrggbb

-0.38

 ujednoznacz

-0.35

"]));

-0.35

LikeLike

-0.35

Життєпис

-0.35

']))

-0.34

POSITIVE LOGITS

 participants

0.52

 psych

0.50

 psychologist

0.48

 psychologists

0.47

Applet

0.47

 Psychologist

0.47

 jsPsych

0.47

parsedMessage

0.46

pal

0.46

 distra

0.45

Activations Density 0.772%

terminology related to cognitive processes and attention

No Comments

No Known Activations