INDEX

Explanations

references to scientific classifications and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/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.10.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

endaft

-0.46

 calendriers

-0.43

webElementXpaths

-0.42

 StringTokenizer

-0.40

AddWithValue

-0.40

})`

-0.40

lateur

-0.39

 péché

-0.39

ARTER

-0.39

 invokingState

-0.38

POSITIVE LOGITS

 British

1.20

British

1.12

英国

1.12

 BRITISH

1.11

 London

1.06

UK

1.05

 Britain

1.04

 british

1.03

イギリス

1.02

 британ

1.02

Activations Density 1.977%

references to scientific classifications and institutions

No Comments

No Known Activations

references to scientific classifications and institutions

No Comments

No Known Activations