INDEX

Explanations

HTML tags and elements appearing in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

SequentialGroup

-0.88

 ſind

-0.82

 indígen

-0.80

 témoig

-0.78

 avoient

-0.76

 Verſ

-0.74

 ſei

-0.74

 Houſe

-0.73

 queſta

-0.73

 chré

-0.72

POSITIVE LOGITS

0.31

0.26

0.25

||

0.25

0.24

is

0.24

or

0.24

—

0.23

 lenker

0.23

Activations Density 0.463%

HTML tags and elements appearing in the document

No Comments

No Known Activations