INDEX

Explanations

references to different times of the day, particularly focusing on the morning

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

AndEndTag

-0.93

makeConstraints

-0.81

 håll

-0.75

/***/

-0.75

HasKey

-0.74

########.

-0.72

catraz

-0.72

 politiet

-0.71

styrelsen

-0.70

bukkit

-0.68

POSITIVE LOGITS

 morning

1.14

 Morning

1.05

 mornings

1.03

 Morn

1.01

 Morgen

1.00

 MORNING

0.97

 evening

0.97

 Afternoon

0.95

morning

0.94

 afternoon

0.90

Activations Density 0.032%

references to different times of the day, particularly focusing on the morning

No Comments

No Known Activations