INDEX

Explanations

technical terms and methodologies related to data processing and analysis in scientific contexts

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

Following data processing/calibration steps

np_acts-logits-general · gemini-2.0-flash

data processing quality calibration

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

gonic

-0.63

mybatisplus

-0.61

 GenerationType

-0.58

Subviews

-0.53

CodedInputStream

-0.52

 ProtoMessage

-0.52

 endowments

-0.51

########.

-0.51

EndProject

-0.51

 anticipo

-0.49

POSITIVE LOGITS

 calibration

1.09

 calibr

0.97

 Calibration

0.95

 validation

0.89

Calibration

0.87

 calibrate

0.85

 recal

0.82

 calib

0.82

 error

0.80

 Validation

0.78

Activations Density 1.759%

technical terms and methodologies related to data processing and analysis in scientific contexts

Following data processing/calibration steps

data processing quality calibration

No Comments

No Known Activations