INDEX

Explanations

terms related to driving and vehicles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ruptcy

-0.78

 bezeichneter

-0.75

 Pronto

-0.65

 Widgets

-0.64

 relativity

-0.64

 QtGui

-0.62

 Ceci

-0.61

SGS

-0.60

XmlAccessorType

-0.59

 Blackout

-0.59

POSITIVE LOGITS

 drives

1.04

 Drives

0.92

 drivers

0.91

 Drivers

0.88

 webdriver

0.86

drives

0.79

Drivers

0.76

 drove

0.75

 Drive

0.74

 drive

0.71

Activations Density 0.075%

terms related to driving and vehicles

No Comments

No Known Activations