INDEX

Explanations

statistical measurements related to mean values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

rungsseite

-0.67

risti

-0.65

 חיצוניים

-0.65

тельство

-0.64

 sonder

-0.63

 arşivlendi

-0.63

 Jard

-0.63

Datuak

-0.63

">//

-0.61

ibouti

-0.60

POSITIVE LOGITS

mean

2.88

 mean

2.82

 Mean

2.81

Mean

2.64

 MEAN

2.43

MEAN

2.42

平均

1.33

 Means

1.24

 median

1.24

 Median

1.22

Activations Density 0.123%

statistical measurements related to mean values

No Comments

No Known Activations