INDEX

Explanations

phrases indicating partial information or limitations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

exitRule

-0.54

 يتيمه

-0.52

:✨

-0.50

hyrchwyd

-0.48

 lenker

-0.48

Cyfeiriadau

-0.48

 Meksiku

-0.47

angliski

-0.47

 سكانية

-0.46

buttonBar

-0.44

POSITIVE LOGITS

uxxxx

0.36

 Caval

0.33

EndContext

0.33

 الاطلاع

0.33

まだまだ

0.33

Cli

0.32

TypedDataSet

0.32

Cli

0.32

 Вікіпе

0.32

‚¬

0.32

Activations Density 0.207%

phrases indicating partial information or limitations

No Comments

No Known Activations