INDEX

Explanations

references to specific television seasons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

ínű

-0.78

luigi

-0.77

 Obrador

-0.76

 Harlow

-0.70

 Flücht

-0.70

%)$

-0.70

 Montmartre

-0.69

 attent

-0.68

poietic

-0.68

 useDispatch

-0.67

POSITIVE LOGITS

 season

1.52

 seasons

1.47

 Season

1.41

 Seasons

1.39

Season

1.29

Seasons

1.29

season

1.26

ASONS

1.26

 SEASON

1.25

SEASON

1.13

Activations Density 0.036%

references to specific television seasons

No Comments

No Known Activations