INDEX

Explanations

technical terms and structures used in programming and data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

itano

-0.50

kas

-0.48

mo

-0.48

multi

-0.48

 constant

-0.47

 multi

-0.47

cier

-0.47

land

-0.46

 Select

-0.44

POSITIVE LOGITS

 AssemblyCulture

1.16

Personendaten

0.76

bootstrapcdn

0.76

ModelAdmin

0.74

ьажоргаш

0.73

ImageContext

0.69

 Мексичка

0.68

 محفوظة

0.68

Diweddarwch

0.67

ArrowToggle

0.67

Activations Density 0.309%

technical terms and structures used in programming and data analysis

No Comments

No Known Activations