INDEX

Explanations

occurrences of structured data formats, particularly those involving objects or arrays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Azevedo

-0.44

 Kirsch

-0.44

 élect

-0.43

 Olsson

-0.43

 Größe

-0.41

EventArgs

-0.41

 Meinung

-0.41

 Velasco

-0.41

 víctima

-0.40

 Kruse

-0.40

POSITIVE LOGITS

 disambiguazione

0.69

 BorderSide

0.68

 BoxDecoration

0.53

":{"

0.50

CppMethod

0.50

IsContent

0.49

SourceChecksum

0.49

httphttps

0.48

ibrill

0.48

 autorytatywna

0.48

Activations Density 0.159%

occurrences of structured data formats, particularly those involving objects or arrays

No Comments

No Known Activations