INDEX

Explanations

terms related to vehicles and their functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

DEAR

-0.56

 Gout

-0.55

 kır

-0.53

weetened

-0.53

 Dans

-0.53

Say

-0.53

arraycopy

-0.53

__(/*!

-0.52

YOND

-0.52

 koron

-0.52

POSITIVE LOGITS

 vehicle

2.89

 vehicles

2.84

 Vehicle

2.71

vehicle

2.63

 Vehicles

2.59

 VEHICLE

2.57

Vehicle

2.55

vehicles

2.52

Vehicles

2.33

VEH

2.18

Activations Density 0.031%

terms related to vehicles and their functionalities

No Comments

No Known Activations