INDEX

Explanations

references to favorite things or preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

-0.64

-0.61

In

-0.60

was

-0.60

it

-0.59

ers

-0.58

dataflow

-0.57

Ducks

-0.57

POSITIVE LOGITS

 favorite

1.89

 favourite

1.80

 favorites

1.79

 Favorite

1.75

favorite

1.71

 Favorites

1.69

favourite

1.67

 Favourite

1.66

 FAVORITE

1.65

Favorite

1.63

Activations Density 0.058%

references to favorite things or preferences

No Comments

No Known Activations