INDEX

Explanations

terms related to driving and movement dynamics

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

ruptcy

-0.74

 McNamara

-0.71

 Templeton

-0.65

 Newberry

-0.64

 dépass

-0.64

Ceci

-0.63

 Orton

-0.62

 McGrath

-0.61

 Deepak

-0.61

 Beauchamp

-0.60

POSITIVE LOGITS

 drives

1.43

 drivers

1.25

 Drives

1.23

drives

1.17

 webdriver

1.13

 drove

1.13

 Drivers

1.12

 drive

1.11

 driving

1.09

drive

1.09

Activations Density 0.182%

terms related to driving and movement dynamics

No Comments

No Known Activations