INDEX

Explanations

references to mathematical constructs or relationships involving variables and operators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Verm

-0.65

 LoginComponent

-0.63

Edg

-0.63

 Stef

-0.63

SIG

-0.63

Gw

-0.63

Stef

-0.62

 trinh

-0.61

 clearColor

-0.61

 Strö

-0.60

POSITIVE LOGITS

1.27

</th>

1.12

</td>

1.05

">&

0.95

>&

0.93

)&

0.93

}&

0.91

InjectAttribute

0.89

%&

0.89

 Havel

0.88

Activations Density 0.083%

references to mathematical constructs or relationships involving variables and operators

No Comments

No Known Activations