INDEX

Explanations

abbreviations, acronyms, and technical definitions related to networking or computer science

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

تقاوى

-0.64

Personendaten

-0.58

 étrangère

-0.58

 مشين

-0.58

UnknownFields

-0.56

 CreateTagHelper

-0.56

 propOrder

-0.56

 alimentaire

-0.56

 červená

-0.56

UnsafeEnabled

-0.56

POSITIVE LOGITS

SharedCtor

0.68

خصة

0.57

EndProject

0.57

winston

0.51

Manbalar

0.48

 honor

0.46

ApiModelProperty

0.46

</thead>

0.45

 ModelExpression

0.45

Gweler

0.44

Activations Density 1.375%

abbreviations, acronyms, and technical definitions related to networking or computer science

No Comments

No Known Activations