INDEX

Explanations

highly rated quality descriptors and standards in relation to services or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SequentialGroup

-0.60

zigen

-0.50

 congé

-0.49

cepan

-0.49

pielt

-0.49

brä

-0.48

pielen

-0.47

äfts

-0.47

ftagPool

-0.47

 Océ

-0.47

POSITIVE LOGITS

 quality

1.42

quality

1.26

 excellence

1.13

 QUALITY

1.11

 Quality

1.05

 kwaliteit

1.04

QUALITY

1.02

Quality

1.01

 kvalitet

1.00

 qualité

0.99

Activations Density 0.232%

highly rated quality descriptors and standards in relation to services or products

No Comments

No Known Activations