INDEX

Explanations

references to legal concepts or actions involving charges and their implications

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

 Taktlose

-0.65

addCriterion

-0.57

ſelf

-0.54

Panamoan

-0.52

fjspx

-0.51

ⓧ

-0.50

setObjectName

-0.50

Nationalité

-0.50

 ListTile

-0.49

 kaarangay

-0.48

POSITIVE LOGITS

you

0.85

him

0.60

us

0.56

me

0.54

 uParam

0.53

we

0.52

 viņ

0.48

enumi

0.46

 your

0.45

 nosotros

0.43

Activations Density 0.617%

references to legal concepts or actions involving charges and their implications

No Comments

No Known Activations