INDEX

Explanations

terms and concepts related to Bayesian statistics and inference

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

Bayesian analysis and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

DEPORTES

-0.44

 Unterschiede

-0.42

__':

-0.41

Differences

-0.38

 Abweich

-0.37

Difference

-0.36

화

-0.35

 springfox

-0.35

 Gästen

-0.35

araoh

-0.35

POSITIVE LOGITS

 Bayesian

0.87

Bayesian

0.81

Bayes

0.66

awtextra

0.61

 nakalista

0.61

 Bayes

0.59

protoimpl

0.58

bayes

0.50

 Posterior

0.49

GEBURTSDATUM

0.49

Activations Density 0.042%

terms and concepts related to Bayesian statistics and inference

Bayesian analysis and methods

No Comments

No Known Activations