INDEX

Explanations

technical terms and definitions related to specific methodologies or concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abestanden

-0.68

 bezeichneter

-0.64

Datuak

-0.62

Rüyada

-0.60

 дописавши

-0.59

 Wikimédia

-0.58

 snippetHide

-0.57

nestjs

-0.57

TagMode

-0.56

 مشارکت‌کنندگان

-0.55

POSITIVE LOGITS

FormTagHelper

0.69

 όπου

0.50

MemoryWarning

0.48

/*++

0.47

Crumb

0.46

AutoField

0.46

 describes

0.46

 where

0.46

 berguna

0.44

 Gorbachev

0.44

Activations Density 0.323%

technical terms and definitions related to specific methodologies or concepts

No Comments

No Known Activations