INDEX

Explanations

indicators of the end of sections or segments in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 препратки

-0.65

Personendaten

-0.63

astéroïdes

-0.63

Чыганаклар

-0.61

MTT

-0.60

 poffe

-0.60

 prosa

-0.60

kloped

-0.58

 الرياضيه

-0.58

protoimpl

-0.58

POSITIVE LOGITS

href

0.61

</tbody>

0.57

the

0.53

IMPORTED

0.47

 ***!

0.37

 ağı

0.36

 confec

0.36

the

0.36

<table>

0.35

&#

0.35

Activations Density 0.039%

indicators of the end of sections or segments in a text

No Comments

No Known Activations