INDEX

Explanations

a variety of activation values indicating potential relevance in contextual phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Waray

-0.69

abetes

-0.64

 viewType

-0.58

Tembelea

-0.58

-0.57

 doInBackground

-0.56

VersionUID

-0.55

-0.52

()

-0.52

POSITIVE LOGITS

<eos>

1.89

<unused60>

1.19

<unused63>

1.17

<unused61>

1.09

</em>

0.81

</code>

0.78

</i>

0.71

</u>

0.64

</blockquote>

0.58

Portály

0.55

Activations Density 0.486%

a variety of activation values indicating potential relevance in contextual phrases

No Comments

No Known Activations