INDEX

Explanations

terms and phrases related to mental health and cognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

-0.80

##############

-0.77

 Canaria

-0.72

 Ferrara

-0.70

 Shearer

-0.68

 Schulz

-0.68

 Felder

-0.65

↵↵↵↵↵

-0.63

 Stephens

-0.62

-0.61

POSITIVE LOGITS

 MIND

1.30

MIND

1.20

 Mind

1.18

 Mindy

1.06

 mind

0.97

 minds

0.97

 Minds

0.97

Mind

0.94

mind

0.92

Personensuche

0.91

Activations Density 0.111%

terms and phrases related to mental health and cognition

No Comments

No Known Activations