INDEX

Explanations

mentions of specific disorders or symptoms associated with health issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 propOrder

-0.45

 noDo

-0.39

 تقد

-0.38

Dearest

-0.35

guess

-0.33

memory

-0.33

kamer

-0.32

taux

-0.32

ज़

-0.32

desen

-0.31

POSITIVE LOGITS

+#+#

0.71

cookieParser

0.56

thenReturn

0.56

 ligiloj

0.52

новниш

0.51

よいよ

0.50

 rospy

0.49

hilation

0.49

Aholisi

0.47

 pihaknya

0.47

Activations Density 0.096%

mentions of specific disorders or symptoms associated with health issues

No Comments

No Known Activations