INDEX

Explanations

terms related to measurement 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 @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

گشت

-0.54

 push

-0.52

ⓧ

-0.51

бло

-0.51

PathParam

-0.50

ODA

-0.49

Mo

-0.49

юрпри

-0.48

mo

-0.47

POSITIVE LOGITS

 precision

1.05

 Accurate

0.99

 PRECISION

0.98

 Precision

0.96

 uſed

0.95

Precision

0.93

 accuracy

0.90

precision

0.90

Accurate

0.90

PRECISION

0.88

Activations Density 0.179%

terms related to measurement accuracy and precision

No Comments

No Known Activations