INDEX

Explanations

structured data or sections in a report or document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

 سكانية

-0.61

 nakalista

-0.56

PreferredItem

-0.54

 propOrder

-0.53

 Monfieur

-0.52

 Infór

-0.51

 متعلقه

-0.51

 CURIAM

-0.50

 autorytatywna

-0.49

Хьажоргаш

-0.49

POSITIVE LOGITS

 trick

0.45

0.40

 recon

0.38

 undis

0.37

Fri

0.36

と思ったら

0.36

 за

0.36

fri

0.35

致

0.35

ConstraintMaker

0.35

Activations Density 0.786%

structured data or sections in a report or document

No Comments

No Known Activations