INDEX

Explanations

statistical analyses and their results

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

 Meksiku

-0.57

TProtocol

-0.57

leetcode

-0.56

ABN

-0.56

urin

-0.54

żeli

-0.54

WinForms

-0.54

liebte

-0.52

atimes

-0.52

PIB

-0.52

POSITIVE LOGITS

 propOrder

0.76

HtmlAttribute

0.65

queryInterface

0.63

 ModelExpression

0.61

 regressions

0.57

IntoConstraints

0.56

 trend

0.55

UnusedPrivate

0.55

 InputDecoration

0.53

 Résultats

0.52

Activations Density 1.856%

statistical analyses and their results

No Comments

No Known Activations