INDEX

Explanations

references to item identifiers or items in lists

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

 TextInputType

-0.79

OGND

-0.64

PRWEB

-0.54

Reprodução

-0.53

Географиясе

-0.53

nought

-0.52

Portály

-0.50

 canst

-0.49

cauc

-0.49

ughty

-0.49

POSITIVE LOGITS

 item

1.19

 Item

1.18

Item

1.13

WidgetItem

1.03

 ITEM

0.99

 Items

0.98

 items

0.96

 getItem

0.96

getItem

0.93

items

0.88

Activations Density 0.053%

references to item identifiers or items in lists

No Comments

No Known Activations