INDEX

Explanations

references to data or discussions related to editing and contributions on platforms like Wikipedia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 ویکی‌آمباردا

-0.57

 MainAxisSize

-0.54

postIndex

-0.53

Tikang

-0.52

:✨

-0.48

 jsPsych

-0.47

EndInit

-0.47

fjspx

-0.46

 समीक्षाओं

-0.45

LookAnd

-0.45

POSITIVE LOGITS

发表于

0.57

 محفوظة

0.55

kussion

0.44

 CURIAM

0.43

consulté

0.40

PhysRevLett

0.36

igshid

0.35

rev

0.35

NewUrlParser

0.35

sem

0.35

Activations Density 0.243%

references to data or discussions related to editing and contributions on platforms like Wikipedia

No Comments

No Known Activations