INDEX

Explanations

structural elements and formatting details in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 ExecuteAsync

-0.62

Autoritní

-0.56

ReusableCell

-0.55

COUVER

-0.54

 fusi

-0.54

pherals

-0.53

roek

-0.52

dust

-0.51

dut

-0.50

leyball

-0.49

POSITIVE LOGITS

makeConstraints

0.43

 suivants

0.42

 destacan

0.41

 برانيه

0.39

MouseAdapter

0.38

 rodillas

0.36

Viited

0.36

 highlights

0.36

 ffilm

0.35

 following

0.35

Activations Density 0.474%

structural elements and formatting details in the text

No Comments

No Known Activations