INDEX

Explanations

terms related to nutritional content and metabolic processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Савезне

-1.40

Personensuche

-1.36

клопе

-1.24

kloped

-1.23

 CreateTagHelper

-1.22

WriteTagHelper

-1.21

SourceChecksum

-1.21

Datuak

-1.18

featureID

-1.17

TagMode

-1.15

POSITIVE LOGITS

0.53

0.50

0.48

0.46

ch

0.45

0.43

...

0.43

in

0.41

and

0.40

Activations Density 30.075%

terms related to nutritional content and metabolic processes

No Comments

No Known Activations