INDEX

Explanations

terms related to accuracy and precision

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

pod

-0.61

pat

-0.60

osh

-0.58

ad

-0.57

Esk

-0.56

da

-0.56

-0.55

das

-0.55

pod

-0.55

POSITIVE LOGITS

 accuracy

1.20

 myſelf

1.20

 Accuracy

1.15

 raiſ

1.12

Efq

1.10

 uſed

1.09

 Accurate

1.08

 itſelf

1.08

 juſ

1.07

curacy

1.07

Activations Density 0.105%

terms related to accuracy and precision

No Comments

No Known Activations