INDEX

Explanations

features and options related to software functionality and user customization

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 deschis

-0.70

 étoit

-0.69

 răm

-0.66

 auroit

-0.65

 avoient

-0.65

tagHelperRunner

-0.65

 feroit

-0.65

 concernés

-0.64

 acestui

-0.63

 altrimenti

-0.62

POSITIVE LOGITS

 auto

1.13

 automatic

1.03

 Auto

1.00

automatic

0.85

 custom

0.84

 Automatic

0.81

 multi

0.80

 dynamic

0.77

 autos

0.76

 anti

0.74

Activations Density 0.832%

features and options related to software functionality and user customization

No Comments

No Known Activations