INDEX

Explanations

concepts related to the mind 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Schröder

-0.78

 Scherer

-0.78

 Pepe

-0.71

zieher

-0.69

exotic

-0.66

 Walsh

-0.66

 Adamson

-0.63

ecutable

-0.63

utscher

-0.63

туга

-0.62

POSITIVE LOGITS

 MIND

1.58

MIND

1.44

 Mind

1.41

 mind

1.32

mind

1.25

 minds

1.24

 Mindy

1.19

Mind

1.18

 Minds

1.15

minds

0.95

Activations Density 0.052%

concepts related to the mind and mental processes

No Comments

No Known Activations