INDEX

Explanations

phrases related to wrapping or enclosing items or content

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

när

-0.30

✌

-0.27

Error

-0.27

FirstResponder

-0.26

POI

-0.26

POC

-0.26

مؤ

-0.25

 prove

-0.25

 Пло

-0.25

CI

-0.25

POSITIVE LOGITS

 wrap

2.20

 Wrap

2.16

 wrapping

2.09

 Wrapping

2.02

wrap

2.00

 wrapped

1.98

Wrap

1.97

 wraps

1.95

 Wraps

1.84

 WRAP

1.83

Activations Density 0.169%

phrases related to wrapping or enclosing items or content

No Comments

No Known Activations