INDEX

Explanations

statistical terminology and results related to data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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



-0.71

onViewCreated

-0.56

 Transfermarkt

-0.54

躇

-0.52

 iconLine

-0.52

########.

-0.51

 propOrder

-0.50

#!/

-0.50

 <<<<<<<<<<<<<<

-0.48

 Tử

-0.48

POSITIVE LOGITS

 average

3.71

average

3.21

Average

3.12

 Average

3.11

 averages

2.83

 AVERAGE

2.72

 averaged

2.70

avg

2.58

 averaging

2.56

AVERAGE

2.55

Activations Density 0.863%

statistical terminology and results related to data analysis

No Comments

No Known Activations