INDEX

Explanations

coded numerical data and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 fourteen

-0.67

 Eighteen

-0.67

 sixteen

-0.63

 Sixteen

-0.61

 незавершена

-0.61

 eighteen

-0.59

 twelve

-0.59

awtextra

-0.58

 Seventeen

-0.58

 Twelve

-0.56

POSITIVE LOGITS

2.28

 five

1.81

 Five

1.80

five

1.60

 Fifth

1.59

 fifth

1.59

 FIVE

1.58

五

1.56

Five

1.56

５

1.54

Activations Density 3.776%

coded numerical data and parameters

No Comments

No Known Activations