INDEX

Explanations

proper nouns, particularly names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.27.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

zb

-0.52

 ujednoznacz

-0.46

 Taille

-0.46

 sodio

-0.45

 propOrder

-0.45

mazoo

-0.45

 kaarangay

-0.44

InteropServices

-0.44

Origen

-0.44

 pinulongan

-0.44

POSITIVE LOGITS

 محفوظة

0.55

ProgressHUD

0.48

 CascadeType

0.47

Lob

0.46

fusc

0.44

 Florent

0.43

 layui

0.43

sbin

0.43

 $\{\

0.42

LOB

0.42

Activations Density 1.322%

proper nouns, particularly names and locations

No Comments

No Known Activations