INDEX

Explanations

references to driving or related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Jpa

-0.59

Rujuakan

-0.56

Legenda

-0.56

اریخ

-0.55

 laget

-0.53

 Seeder

-0.53

ValueStyle

-0.52

 يتيمه

-0.52

OuterClass

-0.52

GOTREF

-0.52

POSITIVE LOGITS

 driving

4.24

 Driving

3.87

Driving

3.76

 drives

3.75

driving

3.71

 drive

3.60

 drove

3.51

 Drives

3.30

drive

3.21

drives

3.19

Activations Density 0.089%

references to driving or related activities

No Comments

No Known Activations