INDEX

Explanations

references to statistical models and methods, particularly in relation to data analysis and estimation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

mainAxisSize

-0.57

iprot

-0.56

wpdb

-0.55

AutoresizingMask

-0.51

ViewFeatures

-0.51

writeHead

-0.48

amazonaws

-0.48

 BoxFit

-0.47

balleur

-0.46

freund

-0.46

POSITIVE LOGITS

Tikang

0.79



0.70

 архивлан

0.60

 modelAndView

0.59

 snippetHide

0.59

 gravure

0.59

 Engen

0.57

новништво

0.55

 للمعارف

0.55

 autorytatywna

0.54

Activations Density 1.469%

references to statistical models and methods, particularly in relation to data analysis and estimation

No Comments

No Known Activations