INDEX

Explanations

legal terminology related to driving offenses and arrests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

SequentialGroup

-0.64

ValueStyle

-0.63

 resourceCulture

-0.58

 defStyle

-0.57

AndEndTag

-0.56

SourceChecksum

-0.53

налу

-0.52

 Provenance

-0.51

[*]

-0.50

DrawerToggle

-0.50

POSITIVE LOGITS

 driver

0.81

 speeding

0.80

 drivers

0.79

 driving

0.79

 traffic

0.78

 Driver

0.77

 Driving

0.77

 distracted

0.76

DUI

0.76

 Drivers

0.76

Activations Density 0.312%

legal terminology related to driving offenses and arrests

No Comments

No Known Activations