INDEX

Explanations

elements related to proper nouns and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 HasFactory

-0.46

הערות

-0.41

AndEndTag

-0.41

nuit

-0.38

 protoimpl

-0.38

 Ressource

-0.36

 Photocase

-0.36

NewUrlParser

-0.36

XmlAccessType

-0.36

POSITIVE LOGITS

el

0.52

 kautta

0.48

 onCreateView

0.48

ely

0.46

 subsidiary

0.45

 mengal

0.44

 doInBackground

0.44

Przypisy

0.43

subs

0.43

 iprot

0.43

Activations Density 1.614%

elements related to proper nouns and technical terms

No Comments

No Known Activations