INDEX

Explanations

terms related to licensing and copyright

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

</thead>

-0.58

apnews

-0.53

IntoConstraints

-0.51

beforeEach

-0.51

іан

-0.51

ToAction

-0.50

 solidari

-0.50

 andato

-0.50

͌

-0.50

ganet

-0.49

POSITIVE LOGITS

 license

4.84

 licence

4.41

 License

4.35

 licenses

4.11

License

3.92

license

3.91

 Licence

3.82

 licences

3.69

 licensing

3.59

 Licenses

3.57

Activations Density 0.069%

terms related to licensing and copyright

No Comments

No Known Activations