INDEX

Explanations

references to programming and mathematical variables or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 bezeichneter

-1.13

=$?

-1.08

endsection

-0.93

<?>>

-0.91

ViewInit

-0.89

__':

-0.88

endpush

-0.88

JdbcTemplate

-0.87

Datuak

-0.87

 {}));

-0.85

POSITIVE LOGITS

<blockquote>

1.29

</em>

1.03

</blockquote>

0.93

0.85

…

0.76

vě

0.72

<em>

0.71

</i>

0.68

</h5>

0.68

HasForeignKey

0.65

Activations Density 0.056%

references to programming and mathematical variables or concepts

No Comments

No Known Activations