INDEX

Explanations

terms related to culinary and food characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

出版年

-0.56

oneofs

-0.54

utilisons

-0.49

 betweenstory

-0.47

 transfieras

-0.47

AndEndTag

-0.45

PreExecute

-0.45

kháu

-0.44

новниш

-0.43

adaptiveStyles

-0.43

POSITIVE LOGITS

hub

1.14

 haven

1.05

 destination

1.02

 hotspot

0.96

 Mecca

0.86

 headquarters

0.86

 birthplace

0.85

 venue

0.84

 spot

0.84

 hangout

0.84

Activations Density 0.411%

terms related to culinary and food characteristics

No Comments

No Known Activations