INDEX

Explanations

phrases that describe weaknesses and tendencies related to personal habits and characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Administrativna

-0.75

andaag

-0.70

\{\\

-0.67

neté

-0.66

']))

-0.65

 sessile

-0.62

'])){

-0.62

 dianteiro

-0.60

 sanitario

-0.60

...')

-0.59

POSITIVE LOGITS

 favorite

0.71

 preferences

0.69

favorite

0.67

particular

0.65

Preferences

0.64

preferences

0.64

癖

0.64

 Preferences

0.62

 habits

0.62

Particular

0.61

Activations Density 0.289%

phrases that describe weaknesses and tendencies related to personal habits and characteristics

No Comments

No Known Activations