INDEX

Explanations

documentation comments and their structural elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

parsedMessage

-0.93



-0.88

Jereo

-0.84

ientras

-0.81

 indígen

-0.81

出版年

-0.79

 مرئيه

-0.78

ніципалі

-0.77

arangay

-0.77

 queſta

-0.76

POSITIVE LOGITS

the

0.63

0.58

0.53

The

0.53

//

0.51

To

0.49

The

0.48

0.47

Activations Density 0.045%

documentation comments and their structural elements

No Comments

No Known Activations