INDEX

Explanations

phrases indicating essential or integral aspects of concepts, processes, or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Roskov

-1.04

verwijspagina

-0.86

 kasarigan

-0.78

 Мексичка

-0.77

windowFixed

-0.76

SharedCtor

-0.74

AutoScale

-0.69

matchCondition

-0.67

AutoScaleMode

-0.67

 viewDidLoad

-0.66

POSITIVE LOGITS

 part

3.06

 portion

2.71

 parts

2.69

part

2.56

 portions

2.46

 parte

2.46

Part

2.23

parts

2.21

portion

2.11

 aspects

2.08

Activations Density 1.397%

phrases indicating essential or integral aspects of concepts, processes, or items

No Comments

No Known Activations