INDEX

Explanations

content related to legal and medical disclaimers or advice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

-0.70

and

-0.60

-0.57

-0.56

to

-0.56

ing

-0.51

as

-0.51

lī

-0.50

 just

-0.50

 nationaux

-0.50

POSITIVE LOGITS

 CreateTagHelper

1.14

Personensuche

1.10

:✨

1.07

 ModelExpression

1.00

parsedMessage

1.00

 ſind

0.98

RectangleBorder

0.98

bibfield

0.95

 kasarigan

0.95

 estekak

0.95

Activations Density 0.545%

content related to legal and medical disclaimers or advice

No Comments

No Known Activations