INDEX

Explanations

graphical elements related to nodes and edges in a diagram

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/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.41.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

principalTable

-0.41

Kjelder

-0.41

Composable

-0.37

DECREF

-0.36

 فريبيس

-0.35

drivers

-0.34

Zaj

-0.34

 feminism

-0.34

TagHelper

-0.33

Zaj

-0.33

POSITIVE LOGITS

出版年

0.47

 HttpNotFound

0.39

 HasFactory

0.37

 Bluffs

0.37

Economy

0.35

 tenerife

0.34

 出版

0.33

كتوبر

0.33

 Economy

0.33

Etymology

0.33

Activations Density 0.421%

graphical elements related to nodes and edges in a diagram

No Comments

No Known Activations