INDEX

Explanations

structured data related to items and their attributes

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

-0.69

 againſt

-0.68

 pleaſure

-0.67

Rüyada

-0.65

 myſelf

-0.63

 Theſe

-0.63

>(

-0.61

 theſe

-0.61

>&

-0.61

>@

-0.60

POSITIVE LOGITS

DoubleQuotes

0.92

</u>

0.82

 }}$}

0.77

󠁿

0.77

}}$

0.77

</sub>

0.76

</strong>

0.73

</h6>

0.73

}})

0.72

--}}

0.71

Activations Density 0.148%

structured data related to items and their attributes

No Comments

No Known Activations