INDEX

Explanations

instances and mentions of examples in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

noir

-0.43

 longtemps

-0.41

 Potatoes

-0.40

Potatoes

-0.40

 ardından

-0.40

 marchandises

-0.39

ranath

-0.39

 nieruchomości

-0.39

 elétrica

-0.39

north

-0.38

POSITIVE LOGITS

 Example

1.20

 example

1.20

example

1.18

Example

1.17

 examples

1.13

 EXAMPLE

1.13

EXAMPLE

1.08

Exemple

0.99

exemple

0.99

 Examples

0.98

Activations Density 0.157%

instances and mentions of examples in various contexts

No Comments

No Known Activations