INDEX

Explanations

mentions of favorites or preferences in various contexts

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

er

-0.79

-0.69

-0.66

ers

-0.65

In

-0.65

-0.64

-0.63

ra

-0.62

in

-0.61

POSITIVE LOGITS

 favorites

1.51

 Favorites

1.50

 favorite

1.45

 Favorite

1.43

 favourite

1.39

 favourites

1.35

 Favourite

1.35

favorites

1.35

favorite

1.35

 FAVORITE

1.34

Activations Density 0.039%

mentions of favorites or preferences in various contexts

No Comments

No Known Activations