INDEX

Explanations

assertive reporting of research findings and expert opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ویکی‌پدی

-0.57

 queſta

-0.55

writeFieldEnd

-0.55

RenderAtEndOf

-0.54

 TMPro

-0.54

ReusableCell

-0.54

 SEDS

-0.54

 AssemblyCompany

-0.54

pergillus

-0.51

 autorytatywna

-0.50

POSITIVE LOGITS

 embreagem

0.36

woordig

0.35

 that

0.35

brigens

0.35

 INCLUDING

0.34

 rằng

0.34

cessite

0.33

 efectivamente

0.33

 CONSEQU

0.33

事实上

0.32

Activations Density 0.895%

assertive reporting of research findings and expert opinions

No Comments

No Known Activations