INDEX

Explanations

food-related terms and descriptions

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

 čierna

-0.52

CloseOperation

-0.47

 Buche

-0.45

currentTarget

-0.43

 tacit

-0.42

Vorlage

-0.42

EditorBrowsable

-0.41

 verbund

-0.41

 autorytatywna

-0.40

butan

-0.40

POSITIVE LOGITS

__":

0.40

vegetables

0.39

 spaghetti

0.38

mix

0.38

 abbond

0.36

 assembling

0.36

ManagedBean

0.35

 Kung

0.34

AsStream

0.34

 aleg

0.34

Activations Density 0.193%

food-related terms and descriptions

No Comments

No Known Activations